Learning to Optimize

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 83

Jun 17, 2026stat.ML

A Solver-Free Training Method for Predict-then-Optimize

We propose a scalable method for training prediction (machine learning) models in the predict-then-optimize paradigm, where model outputs serve as coefficients for a subsequent linear optimization task. Directly minimizing the empirical decision regret is intractable for linear programming and combinatorial optimization since the decision mapping is piecewise constant, and the gradients are zero almost everywhere. While existing methods address this by smoothing the differentiation process, they suffer from scalability issues, since a computationally expensive solver call is required for every gradient evaluation. To address this, we propose a decision-focused learning pipeline based on a measure transformation principle, which yields a new surrogate loss that is completely optimization-solver-free during training. We establish theoretical guarantees, including Fisher consistency and excess risk bounds. Empirically, our method achieves decision quality competitive with state-of-the-art methods while reducing training time by orders of magnitude.

Beichen Wan, Mo Liu

Department of Statistics and Operations Research, University of North Carolina at Chapel Hill, NC, USA.

Predict-Then-Optimize Learning to Optimize Decision-Focused Learning

Jun 9, 2026cs.AI

Learning Splitting Heuristics for Parallel String Solvers

String constraint solvers are crucial for reasoning about string-manipulating programs. However, many practical string constraints are undecidable, and real-world applications often present complex constraints that challenge current solvers. The rise of multi-core architectures offers an opportunity for parallel solving. A key parallel solving method is \emph{cube-and-conquer}, in which the quality of splitting heuristics is critical to effectively dividing the search space. Unfortunately, manually designing the heuristics is labor-intensive, and handcrafted heuristics are often sub-optimal. This paper introduces a data-driven approach to automatically generating splitting heuristics. We frame the problem of selecting a splitting atom as a learning task, using features from input formulas and dynamic data from solver execution. We implement this approach in two popular string solvers, Z3seq and Z3str4, demonstrating that the learned heuristics outperform manually designed ones in the number of solved formulas and the average solving time.

Chenhao Gao, Peisen Yao

The State Key Laboratory of Blockchain and Data Security, Zhejiang University Hangzhou, China

Automated Algorithm Discovery Automated Heuristic Design Learning to Optimize Satisfiability Modulo Theories Constraint Programming

Jun 8, 2026cs.LG

LEAF: A Learning-Enabled ADMM Framework for Accelerated Convex Optimization

We propose LEAF, a learning-enabled ADMM framework for accelerated convex optimization. The key idea is to approximate the Moreau envelope of the objective function using an Input Convex Neural Network (ICNN), resulting in a learned model that preserves convexity and smoothness. This leads to the proposed Moreau Envelope Learning ADMM (MEL-ADMM) and its splitting variant sMEL-ADMM. Unlike existing approaches that learn high-dimensional operators directly, LEAF learns a scalar-valued Moreau envelope, significantly reducing model complexity and improving data efficiency. The framework accommodates a broad class of convex problems with smooth and non-smooth objectives. By embedding convexity explicitly through the ICNN architecture, the proposed approach maintains high approximation accuracy while preserving key structural properties of the optimization problem. Both MEL-ADMM and sMEL-ADMM are developed with theoretical guarantees of convergence and feasibility under the learned model. Rigorous analysis shows that the proposed methods achieve convergence rates comparable to classical ADMM while reducing per-iteration computational cost. Numerical experiments demonstrate up to an order-of-magnitude speedup over state-of-the-art solvers while maintaining low optimality gaps

Binh Nguyen, Trinh Tran, Truong X. Nghiem

Department of Electrical and Computer Engineering, College of Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA

Learning to Optimize Alternating Direction Method of Multipliers Input Convex Neural Networks

Jun 7, 2026cs.LG

Scaling Decision-Focused Learning to Large Problems with Lagrangian Decomposition

Decision-focused learning has shown great promise for addressing predict-then-optimize problems, particularly in the presence of under-specified models. However, its practical deployment is often hindered by high computational costs and limited scalability, as it requires solving a constrained optimization problem for each training instance at every iteration. To address these challenges, we propose a novel framework that incorporates Lagrangian decomposition into the decision-focused learning paradigm. Specifically, we introduce a new surrogate objective along with two loss functions for evaluating and training the underlying prediction model. We further propose two variants of our approach, which offer different trade-offs between computational efficiency and solution quality. Our framework can be seamlessly integrated with standard decision-focused learning methods, including Smart Predict-then-Optimize (SPO+) and Implicit Maximum Likelihood Estimation (IMLE). Through experiments on two standard benchmarks, the multi-dimensional knapsack problem and quadratic portfolio optimization, we demonstrate that our approach achieves competitive performance while remaining amenable to parallelization. In particular, it consistently outperforms traditional decision-focused learning methods on large-scale instances, involving up to eight times more variables than those typically considered in related work. The implementation is available at https://github.com/corail-research/DFL-LD.

Stéphane Eilles-Chan Way, Hugo Percot, Quentin Cappart +2

Polytechnique Montréal, Montreal, Canada · Ecole Polytechnique, Palaiseau, France · UCLouvain, Louvain-la-Neuve, Belgium +2

Predict-Then-Optimize Learning to Optimize Combinatorial Optimization Decision-Focused Learning

Jun 5, 2026eess.SP

Amortized Neural Optimization for Pre-Layout Signal Integrity Design Space Exploration using Differentiable Surrogates

Pre-layout design space exploration (DSE) for high-speed signal integrity (SI) analysis is often limited by the computational cost of simulations and iterative optimization algorithms within modern electronic design automation (EDA) workflows. While machine learning surrogate models accelerate the simulation step, optimizing designs still requires utilizing iterative black-box search methods. This iterative nature scales poorly, making multi-corner sweeps computationally expensive. As a solution, this paper proposes amortized neural optimization (ANO) for pre-layout SI design. ANO entirely eliminates iterative black-box inference by utilizing fully differentiable neural network surrogate models. ANO extracts analytical gradients from the surrogate to train a global optimization policy. Instead of solving the optimization problem repeatedly at inference, the optimization process is learned offline and therefore amortized. Once the ANO policy is trained, it maps different channel contexts directly to near-optimal design parameters in a single deterministic forward pass. The efficiency and accuracy of the ANO framework are demonstrated based on three complex SI design scenarios, including DDR5 decision feedback equalization (DFE), 9-dimensional SerDes Tx/Rx co-equalization, and DDR3 DQS differential pair routing to optimize eye diagram metrics under intra-pair skew constraints. By trading roughly 10% in optimality compared to instance-specific black-box algorithms, it realizes speedups of three to four orders of magnitude. For a large-scale 320,000-instance multi-corner SerDes sweep optimization, ANO collapses what would have taken days of computation using iterative search algorithms into a single batched forward pass that completes in milliseconds. This transforms computationally expensive SI optimization into real-time and interactive pre-layout DSE.

Julian Withöft, Werner John, Emre Ecik +2

Surrogate-Assisted Optimization Electronic Design Automation Learning to Optimize

Jun 4, 2026cs.AI

Multi-ResNets for Subspace Preconditioning in Constrained Optimization

We propose MResOpt, a staged residual neural network architecture for constrained optimization problems. Our architecture fits within predict-complete-correct pipelines and decomposes constraint satisfaction by priority through intermediate re-completion and stage-aware losses. The framework enables domain-informed ordered constraint satisfaction which allows the network to utilize ordinal structure when present. Under an idealized infinite-width regime, we show that our design behaves as sequential Gaussian Process regression. On synthetic QP, QCQP, and SOCP benchmarks, the staged architecture improves high-priority constraint satisfaction across convex and non-convex settings. On line-flow-constrained AC optimal power flow, we introduce a physics-motivated constraint ordering and show that MResOpt supports a learned division of labor that keeps iterates on the equality manifold, achieving substantially lower high-priority violation than reprojected baselines while remaining computationally efficient.

Merve Karakas, Christopher J. Williams, Emmanuel O. Balogun +3

UCLA · University of Oxford · Sunrun† +1

Residual Learning Learning to Optimize Optimal Power Flow Constrained Optimization Constraint Satisfaction

Jun 4, 2026eess.SY

Amortized Nonlinear Model Predictive Control

Nonlinear Model Predictive Control requires solving a constrained nonlinear program (NLP) in real-time at every sampling instant, a computational bottleneck that limits deployment on resource-constrained hardware or at high sampling rates. We address this challenge for the broad class of input-affine nonlinear systems to show that the optimal control move can be approximated by a state-dependent quadratic program (QP) whose cost parameters depend on the current state and reference. We propose a single-network residual-corrector architecture: a state-dependent analytic baseline provides initial QP parameters, and the network learns only the corrections needed to match the full NLP solution; the QP is solved by a differentiable interior-point layer, guaranteeing constraint satisfaction for the first control action. The network is trained offline on data generated by an NLP solver using a hybrid loss that combines supervised imitation and KKT-residual penalties. We validate the approach on a three-link planar robotic arm with Cartesian end-effector tracking, demonstrating orders-of-magnitude speedup over the NLP solver while maintaining comparable tracking performance.

Francesco Pillitteri, Alberto Bemporad

IMT School for Advanced Studies, Lucca, Italy

Robotic Control Nonlinear MPC Learning to Optimize Model Predictive Control Optimal Control

Jun 3, 2026cs.AI

Learning Admissible Heuristics via Cost Partitioning

Admissible heuristics are essential for optimal planning, yet learning them remains challenging due to the risk of overestimation. Cost partitioning combines multiple abstraction heuristics while preserving admissibility, but computing optimal partitions online is expensive. We propose a framework that learns to infer admissible cost partitions by leveraging the Lagrangian dual equivalence between cost partitioning and multiplier prediction. Planning states and patterns are encoded as labelled graphs, and an action-centric variant of the Weisfeiler-Leman algorithm extracts structural feature vectors. A deep architecture with axial self-attention and a softmax output layer maps these features to cost weights that satisfy the partition constraints by construction, ensuring admissibility. Experiments demonstrate reduced node expansions compared to suboptimal partitioning baselines while maintaining strict admissibility. To our knowledge, this is the first machine-learned heuristic guaranteed to be admissible.

Hugo Barral, Quentin Cappart, Marie-José Huguet +1

LAAS-CNRS, Universit´e de Toulouse, CNRS, INSA, Toulouse, France · Polytechnique Montr´eal, Montr´eal, Canada · UCLouvain, Louvain-la-Neuve, Belgium +1

Automated Heuristic Design Learning to Optimize

May 30, 2026cs.NE

Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA

Surrogate-assisted evolutionary algorithms (SAEAs) have been widely used for expensive black-box optimization problems. However, their reliance on rigid and manually designed components limits their flexibility and generalization across tasks. Meta-black-box optimization (MetaBBO) provides a promising paradigm for adaptively configuring algorithmic components. Nevertheless, existing MetaBBO methods usually control only a single component, and few studies have investigated the unified control of multi-component optimizers such as SAEAs. Moreover, the robustness-accuracy trade-off in surrogate modeling, which is crucial for stable early-stage exploration and accurate late-stage exploitation, has rarely been explicitly considered. To address these issues, we propose AdaE-SAEA, an adaptive ensemble surrogate-assisted evolutionary algorithm for expensive multi-objective optimization. AdaE-SAEA embeds SAEA as the low-level optimizer within the MetaBBO framework and jointly controls the infill criterion and ensemble-based surrogate modeling. Specifically, bagging and boosting are designed as surrogate modeling modules to adaptively balance robustness and accuracy across different search phases, while the meta-policy simultaneously selects the infill criterion to enable adaptive sampling decisions. The meta-policy is trained through reinforcement learning with parallel sampling and centralized training, improving both training efficiency and transferability. Experiments on synthetic and real-world problems demonstrate that AdaE-SAEA outperforms state-of-the-art baselines and MetaBBO-based methods. We further verify the effectiveness of TabPFN as the base surrogate model for ensemble learning. To the best of our knowledge, this is the first work to unify the control of surrogate modeling and infill criteria in SAEAs while explicitly addressing the robustness--accuracy trade-off.

Xiao Jin, Yongxiong Wang, Haobo Liu +2

School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, 200093, Shanghai, China · Xinxiang University, 453003, Xinxiang, China · College of System Engineering, National University of Defense Technology, 410073, Changsha, China

Surrogate Modeling Surrogate-Assisted Optimization Learning to Optimize Adaptive Sampling Multi-Objective Optimization

May 29, 2026cs.LG

GLENS: Global Search via Learning from Solver Iterates with Diffusion Models

We consider the problem of generating a large collection of initial guesses for local minima of multimodal non-convex continuous optimization problems. The goal is for these initial guesses to be high-quality (i.e., a numerical solver converges quickly) and diverse (i.e., represent many different local minima). Identifying multiple locally optimal solutions enables flexible downstream decision-making, but typically requires expensive global search. Existing data-driven methods predict initial guesses using only the final converged optima from offline solver runs, which discards information about the local neighborhoods of solutions and limits the available training data. We propose GLENS (Global Search via Learning from Solver Iterates), a data-efficient global search method that leverages intermediate solver iterates as free data augmentation. GLENS consists of two components: a neighborhood structure model that uses diffusion models to learn the local geometry around optima conditioned on problem parameters, and a solver behavior model that learns refinement directions to further guide samples towards nearby optima during diffusion sampling. Experiments on modified non-convex benchmark problems and a two-robot obstacle-avoidance navigation problem show that GLENS generates high-quality initial guesses while preserving the multimodal distribution of diverse local optima. The resulting initial guesses lead to faster solver convergence across different problem settings and solvers. We also analyze how key hyperparameter choices affect the performance.

Anjian Li, Bartolomeo Stellato, Ryne Beeson

Department of Electrical and Computer Engineering, Princeton University, Princeton, 08544, NJ, USA. · Department of Operations Research and Financial Engineering, Princeton University, Princeton, 08544, NJ, USA. · Department of Mechanical and Aerospace Engineering, Princeton University, Princeton, 08544, NJ, USA.

Learning to Optimize Diffusion Sampling Global Optimization Multimodal Optimization Nonconvex Optimization

May 27, 2026cs.AI

KLineage: Recovering the Missing When of Kernel Optimization by Deoptimizing Experts

LLM-based agents are increasingly used to generate GPU kernels, but they often struggle to determine when an optimization is sound because its required code state and dependencies are implicit in expert implementations. We introduce KLineage, which learns this missing "when" knowledge from expert kernels: instead of relying on forward rollouts, KLineage walks expert implementations backward through validation-gated simplifications and reverses each accepted step into a reusable optimization skill. Each skill records not only the optimization intent, but also when to apply the optimization technique, including where it applies in code, what conditions made it valid, what effect it has, and what failures its assumptions avoid. A downstream LLM materializes these skills on new code surfaces under the same compile/correctness/profile gate. This guidance on when to apply each optimization can help downstream models to generate higher-performance kernels. On five expert workloads across two NVIDIA architectures, these lineage-derived skills serve as an effective optimization curriculum, exceeding recent memory-based LLM-kernel baselines in both final kernel quality and optimization efficiency under the same fixed budget. We also demonstrate that the KLineage framework extends beyond NVIDIA GPUs to Ascend NPUs. Our code is publicly available at https://github.com/ict-agent/klineage.

Shuoming Zhang, Qiuchu Yu, Ruiyuan Xu +11

SKLP, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · University of New South Wales

GPU Kernel Optimization GPU Acceleration High-Performance Computing Large Language Model-Guided Optimization Learning to Optimize GPU Kernel Generation+1

May 23, 2026cs.LG

PILOT: Policy-Informed Learned Optimization for Adaptive Deep Network Training

Despite the central role of optimization in deep learning, most optimizers rely on update structures whose functional form is fixed before training begins. This static design can limit their ability to respond to changing gradient behavior across the loss landscape, where training may shift between stable, noisy, and inconsistent regimes. This study proposes PILOT (Policy-Informed Learned OpTimizer), an online optimizer that adapts its update behavior during training. Rather than using a fixed balance between momentum, normalization, and sign-based updates, PILOT uses gradient-direction agreement as a signal of local training stability. Conditioning the update rule on this agreement signal allows the optimizer to adjust its behavior when gradients become stable, noisy, or inconsistent. Experiments on FashionMNIST and CIFAR-10 show that PILOT consistently achieves the highest accuracy among the evaluated optimizers across convolutional settings. On the CNN architecture, PILOT reaches 94.13% on FashionMNIST and 81.94% on CIFAR-10. On ResNet-18, it further improves performance, reaching 95.71% on FashionMNIST and 93.42% on CIFAR-10. These results suggest that learning how to adapt the update structure during training can improve performance across both compact and deeper convolutional models while preserving a simple first-order optimization framework. The implementation of PILOT is publicly available at https://github.com/SattamAltwaim/PILOT.git

Sattam Altuuaim, Lama Ayash, Muhammad Mubashar +1

King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · University of Strathclyde, Glasgow, Scotland

Deep Learning Optimization Learning to Optimize Adaptive Gradient Methods

May 22, 2026cs.LG

An Open-Source Training Dataset for Foundation Models for Black-box Optimization

Most black-box optimization methods require extensive hyperparameter tuning, often limiting their ability to generalize across different optimization domains. Foundation models for black-box optimization that learn optimization principles from a large collection of optimization trajectories offer a promising alternative, with the potential to outperform manually designed methods across diverse problem classes. However, prior work has either relied on non-public datasets or on purely synthetic data, limiting reproducibility and generalization to real-world problems. As a result, progress in this area has been constrained by the lack of large-scale, real-world, publicly available pre-training data. We introduce BBO-Pile, the first open-source dataset comprising over 500K optimization trajectories evaluated across 3095 different black-boxes for different optimizers, which represents by far the largest public dataset for this task. Using this dataset, we train a family of foundation models at multiple scales, ranging from 2M to 80M parameters and from 200M to 2B training tokens, and study their scaling behavior with respect to compute. Our results demonstrate that large-scale pre-training is a viable and effective approach to imitate black-box optimization methods, paving the way for future research in this direction.

Aaron Klein, Herilalaina Rakotoarison, Luca Thale-Bombien +1

University of Helsinki · ELLIS Institute Tübingen, Prior Labs

Black-Box Optimization Learning to Optimize Scaling Laws

May 21, 2026cs.CV

SO-Mamba: State-Ownership Mamba for Unrolled MRI Reconstruction

Accelerated MRI reconstruction requires recovering missing details while preserving anatomically coherent structures across large spatial regions. State-space models such as Mamba provide efficient long-range modeling, making them attractive learned regularizers for unrolled reconstruction. However, in a data-consistency-coupled unrolled solver, different stages operate on different reconstruction iterates, where the resident carrier should preserve coherent reconstruction content across stages while stage-dependent non-resident evidence is tied to the current update. Treating these roles uniformly can place persistent resident-carrier evidence and update-dependent non-resident evidence into the same recurrent content route. We therefore propose SO-Mamba, a state-ownership Mamba regularizer that assigns reconstruction evidence within each Mamba stage to recurrent residency, state-interface access, and non-state output correction. SO-Mamba implements this ownership rule with a State-Ownership Router (SOR), which constructs a resident carrier for recurrent content and routes non-resident evidence to affine modulation of the B/C state interfaces and an output correction outlet. The resident carrier supplies the Mamba content route, while the non-resident evidence stream adapts the state interfaces and contributes through the output outlet without entering the recurrent content route. We further introduce a two-level outer-band leakage diagnostic that separates hidden-state storage from readout expression by measuring outer-band energy in the selective-scan state trajectory and the post-scan Mamba readout. Experiments on five public MRI reconstruction benchmarks spanning diverse anatomies, sampling patterns, and coil configurations show that SO-Mamba consistently improves over CNN-, Transformer-, and Mamba-based baselines with competitive computational efficiency.

Pengcheng Fang, Hongli Chen, Fangfang Tang +3

University of Southampton · University of Queensland · Soochow University

Mamba Learning to Optimize Accelerated MRI Reconstruction

May 20, 2026cs.LG

Learning fMRI activations dictionaries across individual geometries via optimal transport

Dictionary learning is a powerful tool for creating interpretable representations. When applied to functional magnetic resonance imaging (fMRI) data, the resulting patterns of brain activity can be used for various downstream tasks, such as brain state classification or population-level analysis. However, a major challenge is the variability in brain geometry across individuals. This is usually addressed by projecting each individual brain geometry onto a common template, which removes subject-specific information. In this work, we introduce a novel approach to dictionary learning on fMRI data that explicitly accounts for this variability. We use the optimal transport-based Fused Gromov-Wasserstein (FGW) distance to compare graphs with different geometries and features. To address the challenge of computing multiple FGW distances for large graphs such as those arising from fMRI data, we rely on amortized optimization to learn a neural network that predicts an approximation of the optimal transport plans, which substantially reduces the computational cost. Additionally, we learn dictionary atoms that depend on the FGW trade-off parameter, which controls the balance between feature alignment and structural consistency. Numerical experiments on the HCP dataset demonstrate that the proposed approach captures different levels of geometric variability in the data and provides representations that preserve essential information.

Sonia Mazelet, Rémi Flamary, Bertrand Thirion

CMAP, Ecole Polytechnique · Palaiseau, France · Mind, Inria-Saclay

Learning to Optimize Geometric Representation Learning Dictionary Learning Neuroimaging Optimal Transport

May 20, 2026cs.CV

AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting

2D Gaussian splatting provides an efficient explicit representation for image reconstruction, but existing methods still require costly per-image iterative optimization or rely on handcrafted priors for primitive allocation. We present AIR, a self-supervised feed-forward framework that amortizes iterative Gaussian fitting into a single network pass, eliminating per-image test-time optimization. AIR adopts a stage-wise residual architecture that progressively predicts additional Gaussian primitives from reconstruction residuals, together with an explicit Stage Control mechanism that activates new primitives only in under-reconstructed regions. A Predict--Optimize--Distill training strategy stabilizes multi-stage prediction by distilling short-horizon optimized Gaussian increments back into the predictor. The stabilized predictor is then jointly finetuned across stages and equipped with an image-adaptive quantizer for compact Gaussian storage. Experiments on Kodak and DIV2K show that AIR achieves better reconstruction quality than representative Gaussian-based baselines while reducing encoding time to 160--300,ms. Code: https://github.com/whoiszzj/AIR.git

Zhaojie Zeng, Yuesong Wang, Yawei Luo +1

School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China · School of Software Technology, Zhejiang University, Hangzhou, Zhejiang

Learning to Optimize Image Reconstruction Gaussian Splatting

May 18, 2026stat.ML

Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming

Lagrangian Relaxation (LR) is a powerful technique for solving large-scale Mixed Integer Linear Programming (MILP), particularly those with decomposable structures, such as vehicle routing or unit commitment problems. By relaxing the coupling constraints, LR enables parallel subproblem solving and often yields tighter dual bounds than standard linear programming relaxations, which is crucial for efficient branch-and-bound pruning. While recent empirical work has shown promising results using machine learning to predict these multipliers, a theoretical understanding of such methods remains an open question. In this work, we bridge this gap by analyzing the problem of learning LR through the lens of Data-driven Algorithm Design, i.e., a statistical learning problem over a distribution of problem instances. Our contributions are as follows: first, we derive a generalization bound of

\mathcal{O}(s^{1.5}/\sqrt{N})

for the learned multipliers, where

s

is the number of coupling constraints and

N

is the sample size. Second, we provide a minimax lower-bound of

Ω(s/\sqrt{N})

, proving that a linear dependency is unavoidable. Third, we constructively close this theoretical gap by proving that Stochastic Gradient Ascent (SGA) with averaging achieves the minimax optimal rate

Θ(s/\sqrt{N})

. Finally, we extend our framework to the learning-to-warm-start setting, proving that it achieves a fast, minimax-optimal rate of

Θ(s/N)

and establishing a theoretical advantage over direct multiplier prediction.

Tung Quoc Le, Anh Tuan Nguyen, Viet Anh Nguyen

Université Grenoble Alpes, LJK, CNRS, Grenoble INP, 38000 Grenoble, France · Carnegie Mellon University, Machine Learning Department · Chinese University of Hong Kong, Department of Systems Engineering and Engineering Management.

Mixed-Integer Linear Programming Learning to Optimize Constrained Optimization Linear Programming Learning-Augmented Algorithms

May 18, 2026cs.LG

Agentic Cost-Aware Query Planning with Knowledge Distillation for Big Data Analytics

Query optimization in big data analytics remains computationally expensive, particularly for resource-constrained environments where traditional optimizers fail to satisfy memory and latency constraints. We present an agentic query planning system that combines a rule-based teacher planner, UCB1 bandit exploration, cost-aware prediction, and knowledge distillation to a lightweight student planner. Our teacher planner generates SQL plans using six key optimization strategies, while UCB1 bandit search efficiently explores the plan space under explicit resource constraints. A Random Forest cost model predicts query latency from plan features, enabling cost-aware decisions. A distilled student planner (Logistic Regression or Gradient Boosting) learns to mimic teacher-bandit decisions for fast inference. Evaluation on NYC Taxi and IMDB datasets demonstrates 23% latency reduction compared to default planners while maintaining 94% constraint satisfaction. The student planner achieves 89% accuracy in replicating optimal plans with 15x faster inference time. Our single-file implementation enables reproducible big-data analytics on resource-limited machines and is publicly available at https://github.com/mahdinaser/agentic-kd-planner.

Mahdi Naser-Moghadasi

Research Division, BrightMind AI, Seattle, WA · Texas Tech University, Lubbock, TX

Learning to Optimize

May 15, 2026cs.GT

Misspecified Estimate-then-Optimize Leads to Supra-Competitive Prices

We study whether simple algorithmic pricing systems can systematically produce collusive-like prices in multi-firm markets. We consider firms that price using a myopic estimate-then-optimize rule: each repeatedly fits a demand model to its own price and sales history and sets the price that maximizes estimated profit. This demand model is misspecified, omitting competitors' prices. We analyze the dynamics of this rule when it is initialized by an exploration phase of independent random prices. We characterize when this pipeline converges to supra-competitive prices above the Nash equilibrium, via a fluid-limit ordinary differential equation analysis. We show that supra-competitive prices arise when firms initially explore within similar price ranges on the same side of the Nash price. Moreover, prices can be substantially above the Nash price; we show that prices can reach monopoly levels under symmetric exploration. Simulations calibrated to a real multifamily rental market confirm that supra-competitive outcomes arise robustly beyond our theoretical assumptions, including under finite horizons, heterogeneous products, and nonlinear logit demand.

Jackie Baek, Vivek F. Farias, Farrell Wu

Stern School of Business, New York University · Massachusetts Institute of Technology

Predict-Then-Optimize Learning to Optimize Algorithmic Collusion Dynamic Pricing

May 15, 2026cs.CV

Learn2Splat: Extending the Horizon of Learned 3DGS Optimization

3D Gaussian Splatting (3DGS) optimization is most commonly performed using general-purpose first-order optimizers such as Adam or SGD. Although robust across scenes, they update each parameter independently without exploiting the structural and spatial relationships among Gaussians, which slows convergence. Recent works introduced learned optimizers that predict correlated updates informed by inter-parameter and inter-Gaussian dependencies. However, those are trained for a fixed number of optimization iterations and rely on manually scheduled learning rates to avoid degradation. In this paper, we introduce Learn2Splat, a learned optimizer for 3DGS that avoids degradation over extended optimization horizons without auxiliary mechanisms. To enable this, we propose a meta-learning scheme that extends the optimization horizon via a checkpoint buffer and an optimizer rollout strategy, combined with an architecture that encodes gradient scale information in its latent states. Results show higher novel view synthesis quality at equal wall-clock time, while remaining stable over long horizons, with zero-shot generalization to unseen datasets and settings. To support our findings, we build a unified framework to train and evaluate learned and standard optimizers across sparse and dense view settings. Code and models will be released publicly. Our project page is available at https://autonomousvision.github.io/learn2splat .

Naama Pearl, Stefano Esposito, Haofei Xu +6

University of Tübingen, Tübingen AI Center · ETH Zurich · Meta Reality Labs

3D Gaussian Splatting Meta-Learning Learning to Optimize Novel View Synthesis

May 14, 2026eess.IV

DIPA: Distilled Preconditioned Algorithms for Solving Imaging Inverse Problems

Solving imaging inverse problems has usually been addressed by designing proper prior models of the underlying signal. However, minimizing the data fidelity term poses significant challenges due to the ill-conditioned sensing matrix caused by physical constraints in the acquisition system. Thus, preconditioning techniques have been adopted in classical optimization theory to address ill-conditioned data-fidelity minimization by transforming the algorithm gradient step to achieve faster convergence and better numerical stability. We extend the preconditioning concept beyond convergence acceleration and use it to improve reconstruction quality. We introduce DIPA: Distilled Preconditioned Algorithms, where a preconditioning operator (PO) is optimized using teacher-guided distillation criteria. Unlike standard model-compression KD, the teacher and student differ by the sensing operators available during reconstruction: the teacher uses a simulated, better-conditioned, and more informative sensing matrix, whereas the student uses the physically feasible sensing matrix. We design different distillation loss functions to transfer different properties of the teacher algorithm to the preconditioned student. The PO can be linear (L-DIPA), allowing interpretability, or non-linear (N-DIPA), parametrized by a neural network, offering better scalability. We validate the proposed PO design across several imaging modalities, including magnetic resonance imaging, compressed sensing, and super-resolution imaging.

Romario Gualdrón-Hurtado, Roman Jacome, Leon Suarez +1

Department of Computer Science, Universidad Industrial de Santander, Bucaramanga, 680002, Colombia · Department of Electrical Engineering, Universidad Industrial de Santander, Bucaramanga, 680002, Colombia

Learning to Optimize Image Reconstruction Knowledge Distillation Image Inverse Problems

May 13, 2026cs.CV

Learning to Optimize Radiotherapy Plans via Fluence Maps Diffusion Model Generation and LSTM-based Optimization

Volumetric Modulated Arc Therapy (VMAT) is a cornerstone of modern radiation therapy, enabling highly conformal tumor irradiation and healthy-tissue sparing. Yet, its planning solves inverse and nested optimization for multi-leaf collimators, monitor units and dose parameters, while enforcing their consistency to ensure mechanical deliverability. Nevertheless, this process often requires repeated re-optimization when treatment configurations change, resulting in substantial planning time per patient. To address these problems, we present a diffusion-driven Learning-to-Optimize (L2O) method for end-to-end VMAT planning. A distribution-matching distilled diffusion model learns a clinically feasible manifold of fluence maps, enabling their one-shot generation. On top of this, an LSTM-based L2O module learns gradient update dynamics to swiftly refine fluence maps toward prescribed dose objectives during inference. Experimental results on clinical and public prostate cancer cohorts demonstrate improved planning efficiency, flexibility, and machine deliverability over currently available end-to-end VMAT planners.

Isabella Poles, Simon Arberet, Riqiang Gao +5

Politecnico di Milano, Milan, Italy · Digital Technology and Innovation, Siemens Healthineers, Princeton, NJ, USA · Digital Technology and Innovation, Siemens Healthineers, Erlangen, Germany

Learning to Optimize Oncology Diffusion Models

May 13, 2026cs.LG

Local Inverse Geometry Can Be Amortized

Nonlinear inverse problems often trade inexpensive but fragile first-order updates against curvature-aware methods such as Gauss-Newton and Levenberg-Marquardt, which obtain stronger directions by repeatedly solving Jacobian-based linearized systems. We propose a learned alternative: amortize local inverse geometry into a reusable reverse operator. Our framework learns a bidirectional surrogate, Deceptron, and deploys it through D-IPG (Deceptron Inverse-Preconditioned Gradient), an iterative solver that pulls residual-corrected measurement-space proposals back to latent space. The key mechanism is a Jacobian Composition Penalty (JCP), which trains the reverse Jacobian to act as a local left inverse of the forward Jacobian; its runtime counterpart, RJCP, measures the same inverse-consistency error along optimization trajectories. We prove that D-IPG is first-order equivalent to damped Gauss-Newton under local pseudoinverse consistency, with deviation controlled by composition error and conditioning. Across seven PDE inverse-problem benchmarks, D-IPG outperforms standard baselines, achieves 94.8% mean success across the six-problem reliability suite, and reaches comparable or better recovery quality at up to 77x lower inference-time solve cost on the main benchmarks.

Aaditya L. Kachhadiya

Independent Researcher Surat, India

Neural Surrogate Modeling Inference-Time Optimization Amortized Inference Learning to Optimize PDE Inverse Problems

May 13, 2026cs.NI

NeuroRisk: Physics-Informed Neural Optimization for Risk-Aware Traffic Engineering

In production Wide-Area Networks (WANs), correlated failures dominate availability losses, forcing operators to reserve large safety margins that leave substantial capacity underutilized. Achieving high utilization under strict availability targets therefore requires risk-aware Traffic Engineering (TE) over dozens to hundreds of probabilistic failure scenarios-yet solving this problem at operational timescales remains elusive. We demonstrate that existing risk-aware formulations can be unified under an embedded Sort-and-Select structure, exposing a fundamental trade-off between expressiveness and tractability: classical optimizers either restrict scenario selection for efficiency or incur prohibitive decomposition costs. While deep learning appears promising, prior Deep TE methods mainly target maximum link utilization and rely on scaling-based feasibility, which fundamentally breaks under explicit capacity constraints and scenario-dependent risk. We present NeuroRisk, a physics-informed deep unrolled optimizer that exploits the structure of Sort-and-Select. NeuroRisk enforces feasibility via gated edge-local reservations and represents scenario sets through permutation-invariant, gradient-aligned cues. Evaluations on production-style WANs show that NeuroRisk achieves small optimality gaps relative to the solver with orders of magnitude speedup

(10^2- 10^5 \times)

on risk objectives, while outperforming neural baselines on nominal throughput.

Yingming Mao, Ximeng Liu, Jingyi Cheng +8

Xi’an Jiaotong University · Shanghai Innovation Institute · Shanghai Jiao Tong University +2

Stochastic Optimization Neural Network Optimization Learning to Optimize

May 11, 2026cs.AI

Low-Cost Labels, Reliable Choices: Rollout-Calibrated Hyper-Heuristics for Job Shop Scheduling

Learning-assisted hyper-heuristics can select among dispatching rules while preserving the feasibility and interpretability of constructive Job Shop Scheduling Problem (JSSP) heuristics. Their main computational cost lies in label generation rather than model fitting, since each supervised label usually requires rolling out candidate rules from a partial schedule. We study this label-cost problem together with a reliability problem: a learned selector should not switch away from a strong default rule unless the predicted gain is credible. The proposed selector uses regret-normalized rollout labels, a contextual KNN uncertainty estimate, and a gate that acts only when the predicted improvement exceeds an uncertainty-adjusted margin. We also vary rollout depth and breadth to measure the cost-quality trade-off. On synthetic JSSP instances, the gated selector achieves the lowest mean RPD among learned selectors, remains close to the best fixed dispatching rule, and reduces Random-HH mean RPD by more than an order of magnitude.

Junhao Wei, Yanxiao Li, Yifu Zhao +8

Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China · College of Animal Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China · 4Macao Polytechnic University, Macao, 999078, China

Selective Prediction Metaheuristic Optimization Learning to Optimize Learning-Augmented Algorithms Job Shop Scheduling

May 11, 2026cs.AI

LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs

Efficient branching policies are essential for accelerating Mixed Integer Linear Programming (MILP) solvers. Their design has long relied on hand-crafted heuristics, and now machine learning has emerged as a promising paradigm to automate this process. However, existing learning-based methods are often hindered by their dependence on expensive expert demonstrations and the gap between training objectives and the solver's end-to-end performance. In this work, we propose LLM4Branch, a novel framework that leverages Large Language Models (LLMs) to automate the discovery of efficient branching policies. Specifically, the discovered policy is an executable program with a program skeleton generated by the LLM and a parameter vector, which is optimized via a zeroth-order method over a few instances with their end-to-end performance feedback. Extensive experiments on standard MILP benchmarks demonstrate that LLM4Branch establishes a new state-of-the-art among CPU-based methods and achieves performance competitive with advanced GPU-based models. Codes are available at https://github.com/hzn18/LLM4Branch.

Zhinan Hou, Xingchen Li, Yankai Zhang +2

Department of Automation, BNRist, Tsinghua University, Beijing, China.

Branch and Bound Mixed-Integer Linear Programming Large Language Model-Guided Optimization Learning to Optimize LLM-Based Program Synthesis Integer Linear Programming

May 9, 2026stat.ML

Tight Generalization Bounds for Noiseless Inverse Optimization

Inverse optimization (IO) seeks to infer the parameters of a decision-maker's objective from observed context--action data. We study noiseless IO, where demonstrations are generated by a ground-truth objective. We provide a high-probability

{O}(\frac{d}{T})

generalization bound for the induced action set, where

d

is the number of unknown parameters and

T

is the size of the training dataset. We strengthen these guarantees under additional conditions that ensure uniqueness of the chosen action, bringing our IO guarantees in line with best-arm identification results in the bandit literature. We further show that the

{O}(\frac{d}{T})

rate is tight over all consistent estimators considered here, and extend the result to both instantaneous and cumulative regret. Notably, the resulting regret lower bound matches the corresponding upper bounds in the adversarial setting, indicating that the stochastic IO setting is effectively adversarial for the class of estimators studied here. Finally, we propose a parameter-free algorithm with lower per-iteration complexity than generic solvers. Experiments validate the predicted rates and illustrate the tightness of our bounds.

Pouria Fatemi, Hoomaan Maskan, Suvrit Sra +1

Technical University of Munich, Germany · Uppsala University, Sweden · University of Toronto, Canada

Parameter Estimation Learning to Optimize Regret Minimization Generalization Bounds

May 7, 2026cs.LG

When Descent Is Too Stable: Event-Triggered Hamiltonian Learning to Optimize

Fixed-budget nonconvex optimization can fail not because local descent is unstable, but because it is too stable: after reaching a nearby stationary point, an optimizer may spend the remaining evaluations refining an uninformative local minimum. We formulate this failure mode as a control problem over optimizer dynamics, where the learner must decide when to descend, when to exploit a promising basin, and when stagnation should trigger movement elsewhere. We introduce SHAPE, a structured adaptive port-Hamiltonian task-family optimizer for event-triggered minima hunting under local information. Starting from gradient-descent dynamics, SHAPE lifts optimization to an augmented phase space

(q, p)

, where the primal state

q

represents the candidate solution, the cotangent variable

p

carries directional sensitivity, and a controller

u

provides processed information from current gradient oracle. Within each stage, a learned Hamiltonian vector field induces structured local descent; across stages, a fixed event clock in the implementation updates ports and memory when local equilibria are detected, with stage-dependent horizons treated in the analysis as a direct generalization. This design preserves a passivity-compatible structure while allowing the same trained policy to use clean, stochastic, or estimated gradient inputs. Experiments on fixed-budget nonconvex optimization tasks show that SHAPE improves best-so-far performance compared with fixed-policy optimizers. These results suggest that adaptive Hamiltonian energy shaping provides a principled mechanism for balancing descent, exploration, and budget allocation in difficult optimization landscapes.

Yi Wang, Chandrajit Bajaj

1Oden Institute · Department of Computer Science

Dynamical Systems Learning to Optimize Nonconvex Optimization Event-Triggered Control Port-Hamiltonian Systems Hamiltonian Dynamics

May 7, 2026cs.LG

Distributionally-Robust Learning to Optimize

We propose a distributionally robust approach to learning hyperparameters for first-order methods in convex optimization. Given a dataset of problem instances, we minimize a Wasserstein distributionally robust version of the performance estimation problem (PEP) over algorithm parameters such as step sizes. Our framework unifies two extremes: as the robustness radius vanishes, we recover classical learning to optimize (L2O); as it grows, we recover worst-case optimal algorithm design via PEP. We solve the resulting problem with stochastic gradient descent, differentiating through the solution of an inner semidefinite program at each step. We prove high-probability bounds showing that the true risk of the learned algorithm is at most the in-sample L2O optimum plus a slack that shrinks with the sample size, and is no worse than the worst-case PEP bound. On unconstrained quadratic minimization, LASSO, and linear programming benchmarks, our learned algorithms achieve strong out-of-sample performance with certifiable robustness, outperforming both worst-case optimal and vanilla L2O baselines.

Vinit Ranjan, Jisun Park, Bartolomeo Stellato

Department of Operations Research and Financial Engineering, Princeton University. · Department of Operations Research and Financial Engineering, Princeton University, and Research Institute of Mathematics, Seoul National University. · Research Institute of Mathematics, Seoul National University.

Learning to Optimize Distributionally Robust Optimization Robust Optimization Wasserstein Distributionally Robust Optimization

Apr 30, 2026cs.LG

NLPOpt-Net: A Learning Method for Nonlinear Optimization with Feasibility Guarantees

Nonlinear Parametric Optimization Network (NLPOpt-Net) is an unsupervised learning architecture to solve constrained nonlinear programs (NLP). Given the structure of an NLP, it learns the parametric solution maps with guaranteed constraint satisfaction. The architecture consists of a backbone neural network (NN) followed by a multilayer (

k

-layered) projection. While the NN drives toward optimality through a loss function consisting of a modified Lagrangian augmented with a consistency loss, the projection ensures feasibility by projecting the NN predictions in the original constraint manifold. Instead of typical distance minimization, our projection exploits local quadratic approximations of the original NLP. Under certain conditions (such as convexity), the projection has a descent property, which improves the NN predictions further. NLPOpt-Net deploys an inversion-free, modified Chambolle-Pock algorithm to solve the constrained quadratic projections during the forward pass and uses the implicit function theorem for efficient backpropagation. The fixed structure of the projection further allows decoupling of the NN and the projection once the training is complete. NLPOpt-Net solves large-scale convex QP, QCQP, NLP, and nonconvex problems with near zero optimality gap and constraint violations reduced to machine precision. Additionally, it provides near accurate prediction of the active sets and corresponding dual variables, thereby enabling a scalable approach for multiparametric programming. Compiling the projection in C provides order of magnitude improvement in inference time compared to JAX. We provide the codes and NLPOpt-Net as a ready to use package that includes GPU support.

Bimol Nath Roy, Rahul Golder, MM Faruque Hasan

Texas A&M University

Neural Network Optimization Learning to Optimize Constrained Optimization Differentiable Optimization