Overview

Bilevel optimization models decisions in two levels: an outer problem evaluates choices using the solution of an inner problem, as in hyperparameter tuning, data selection, meta-learning, and neural architecture search. Common approaches differentiate through inner optimization using unrolling or implicit hypergradients, while single-loop stochastic, penalty-based, and derivative-free methods aim to reduce computation and handle larger or black-box problems. Applications also use the framework for decision-focused learning, reinforcement learning, and strategic settings where one agent responds to another. A central challenge is making these methods efficient and reliable when the inner problem is nonconvex or has multiple solutions, while establishing useful convergence and generalization guarantees without restrictive assumptions.

Latest papers

96 papers10 papers in the last four weeks, down 23% on the four weeks before. 0.1% of all new papers.

Aug 24, 2026

SGHA: A Single-Loop Fully First-Order Algorithm for Nonconvex-Strongly-Convex Bilevel Optimization

In this work, we study the oracle complexity of finding an εε-stationary point for nonconvex-strongly-convex (NC-SC) bilevel optimization using only first-order oracles. Existing methods achieving the best-known complexity guarantees typically rely on double-loop, penalty-based procedures. We propose a novel single-loop algorithm based on a constrained reformulation in which lower-level stationarity is imposed as a constraint. Specifically, we construct a regularized Lagrangian by introducing a quadratic regularizer and restricting the dual variable to a bounded domain, and then apply Smoothed Gradient Descent Ascent [Zhang et al., 2020], with Hessian-vector products approximated via finite differences of gradients. We refer to the resulting deterministic and stochastic algorithms as SGHA and Stoc-SGHA, respectively. In the deterministic setting, SGHA achieves an oracle complexity of O(κˉy5ε−2)O(\barκ_y^{5}ε^{-2}), where κˉy\barκ_y denotes the relevant condition number. In the stochastic setting, Stoc-SGHA achieves an oracle complexity of O(κˉy17ε−6ρ−3)O\left(\barκ_y^{17}ε^{-6}ρ^{-3}\right) with probability at least 1−ρ1-ρ for any ρ∈(0,1)ρ\in(0,1), and an oracle complexity of O(κˉy17ε−6)O\left(\barκ_y^{17}ε^{-6}\right) in expectation under an additional bounded-iterate assumption. Moreover, under an additional stochastic smoothness assumption imposed only on the lower-level objective, the stochastic oracle complexity of Stoc-SGHA improves to O(κˉy11ε−4ρ−2)O\left(\barκ_y^{11}ε^{-4}ρ^{-2}\right) with high probability and O(κˉy11ε−4)O\left(\barκ_y^{11}ε^{-4}\right) in expectation, matching the εε-dependence of the lower bounds.
Aug 14, 2026

Designing Compact Neural Architectures via Neuron Gating and Mixed Activation

Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters using training loss. However, NAS is computationally expensive due to discrete architectural decisions, exponentially growing search spaces, and the high cost of training candidate architectures. This work develops a general bilevel optimization framework for NAS across diverse architectures, including MLPs, CNNs, RNNs, and Transformers, to identify compact architectures with strong predictive performance. We propose three scalable formulations that replace discrete neuron- and activation-level decisions with continuous relaxations, enabling differentiable optimization over otherwise combinatorial architecture spaces. These formulations give rise to three NAS methods: NAS based on Neuron Gating (NAS-NG), NAS based on Mixed Activation (NAS-MA), and NAS based on Neuron Gating and Mixed Activation (NAS-NGMA). Experiments on MLPs and CNNs using MNIST and CIFAR-10 show that the proposed methods consistently identify compact architectures with competitive or improved predictive performance. On MNIST, NAS-NGMA achieves 98.68% test accuracy with 7.69M MLP parameters, while NAS-NG achieves 99.63% accuracy with only 0.26M CNN parameters. On CIFAR-10, the proposed methods consistently outperform vanilla DARTS. Further experiments demonstrate that NAS-NG can optimize substantially over-parameterized and literature-optimal architectures, improving accuracy while reducing parameters. These results establish relaxed bilevel optimization as a scalable alternative to discrete NAS and provide a general framework for efficient neuron- and activation-level architecture optimization.
Aug 13, 2026

Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level

Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning. Although recently some works have been begun to study the multi-objective bilevel optimization, the proposed methods rely on the (strongly) convex lower level problems. In fact, these multi-objective bilevel learning problems are generally nonconvex, and particularly their lower level problems are nonconvex. To fill this gap, we propose a class of Multi-Objective Moreau Envelope based Hessian-free Algorithms (MOMEHA) for the multi-objective bilevel learning problems with nonconvex lower level. Specifically, our method uses the Moreau envelope to relax the original problem into a multi-objective single-level optimization with an envelope constraint. In particular, our method retains computational advantages of being single-loop and Hessian-free in the multi-objective setting by incorporating a smooth weighted Tchebycheff scalarization. Furthermore, we propose a momentum-based variant of MOMEHA (i.e., MB-MOMEHA) method for the stochastic multi-objective bilevel learning problems. In theory, we provide the convergence properties of our algorithms under both deterministic and stochastic setting. Some experiments on few-shot meta-learning and neural architecture search demonstrate that our methods outperform the existing approaches in Pareto front, validating its effectiveness and robustness.
Aug 12, 2026

Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks

Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models. Beyond perturbation generation, transferability is fundamentally governed by the coupling of initialization, surrogate adaptation, and gradient dynamics. We revisit this challenge from a bilevel-minimax perspective and propose BMAT (Bilevel-Minimax Adversarial Transfer). The bilevel formulation captures the dependency between initialization and perturbation, while the inner minimax problem promotes surrogate robustness for cross-architecture generalization. Algorithmically, we develop an integrated bottom-up solver that combines a Soft Weight Modulator and an Implicit Gradient Approximator to enable ternary coupling among initialization, surrogate adaptation, and perturbation optimization. We further provide theoretical insights into the optimization dynamics of the proposed bilevel-minimax framework. Extensive experiments on classification and segmentation benchmarks show that BMAT outperforms more than 10 strong baselines across more than 30 victim models, improving both intra- and cross-architecture transfer and yielding up to a 2x reduction in mIoU. Code is available at https://github.com/callous-youth/BMAT.
Aug 11, 2026

Efficient Hypergradient Descent for Inverse Reinforcement Learning

Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations. A natural approach is to formulate IRL as a bilevel optimization problem, in which the inner level corresponds to policy optimization under the learned reward and the outer level measures the discrepancy between the induced policy and expert data. However, this formulation is computationally challenging in practice because the outer update requires a hypergradient involving an inverse-Hessian-vector product for the inner objective. We address this challenge by showing that, at the inner optimum, the Hessian of the inner objective is proportional to the Fisher information matrix of the policy, yielding a structured Fisher-based hypergradient closely related to Natural Hypergradient Descent. To address the resulting scalability bottleneck associated with large Fisher matrices, we approximate the required inverse-Fisher-vector product using a streaming spectral sketch, avoiding explicit construction of the Fisher matrix. We evaluate our approach against a first-order stochastic bilevel baseline across discrete- and continuous-control environments. The results demonstrate competitive policy performance and strong reward-ranking quality, while Fisher sketching reduces curvature-storage complexity and can improve computational efficiency relative to an explicit Fisher solver.
Aug 7, 2026

Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration

Preference alignment often makes large language models (LLMs) overconfident and poorly calibrated. Traditional post-hoc temperature scaling is inherently domain-dependent: a temperature fitted on one domain does not generalize across domains. This motivates us to modify model parameters during training to improve calibration. We propose maximizing the entropy of predictive distributions as the calibration objective, which directly targets overconfidence by discouraging overly concentrated predictions. Inspired by temperature scaling, we realize this through a bilevel optimization formulation, where the lower level trains the model under a parametric loss and the upper level selects loss hyperparameters to maximize entropy. To make the framework practical at LLM scale, we adopt an efficient first-order approximation that avoids explicit second-order computation. Across both multiple-choice and open-ended generative question answering, experiments demonstrate that our method yields well-calibrated LLMs with particular advantages in out-of-domain generalization.
Aug 4, 2026

Exploiting Separability in Multi-Scale Grey-Box Bayesian Optimization

We consider grey-box optimization problems where the decision variables naturally partition into black-box variables (as arguments to an expensive black-box function) and white-box variables, governed by a set of explicit, closed-form equations that also depend on the output of the black-box function. We exploit this separability through a bilevel reformulation: an outer Bayesian optimization (BO) to optimize the scalar objective as a function of black-box variables alone, while an inner problem solves the white-box subproblem via global optimization. The Gaussian process surrogate used in BO is therefore defined rather than and white-box constraints are satisfied exactly whenever the inner optimizer converges to a feasible point---without penalty functions, chance constraints, or moment approximations. On a suite of 13 benchmark problems, bilevel BO achieves lower regret, with fewer iterations and wall clock time. This advantage is robust to initialization set size, exploration parameters, and inner-solver choice.
Jul 30, 2026

Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity

Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hierarchical task decomposition, and reinforcement learning from human feedback (RL-HF). Most of the bilevel RL algorithms are either not scalable because of using hypergradient with Hessian, or they suffer from high sample complexity because of using penalty-based approximation methods. In this work, we propose a hypergradient-based bilevel RL algorithm using the optimality of the Boltzmann policy for the entropy regularized discounted RL objective function. Our proposed algorithm is Hessian-free and obtains an iteration complexity of O(ε−1)O(ε^{-1}) and state-of-the-art sample complexity of O~(ε−2)\tilde{O}(ε^{-2}) under mild regularity conditions. Further, in our convergence analysis, we are able to remove the assumption of the Polyak-Lojasiewicz (PL) condition on the outer-level objective function present in the prior state-of-the-art sample complexity work.
Jul 26, 2026

SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problems

LLM-based automated heuristic design (AHD) typically scores executable programs on complete instances or within fixed solver components. In large-scale routing problems, localized reconstruction reduces the size of each optimization task, but repair regions within the same incumbent can exhibit substantially different structures. One construction rule must therefore compromise across them. In this paper, we propose SpecAHD, a coupled bilevel framework for within-instance specialization. An upper-level search learns where to expose bounded repair regions, while a lower-level search evolves a complementary repertoire of executable heuristics for the induced repair tasks. The upper-level program determines the repair tasks seen by the lower level, while checked repair outcomes determine how upper-level programs are evaluated. The lower-level objective favors heuristics that perform well on average or solve tasks that the current repertoire handles poorly. For the repair tasks induced by a fixed upper-level program and a fixed lower-level candidate pool, this objective is monotone submodular, allowing greedy repertoire selection with a (1-1/e) approximation guarantee. Across four routing problems and multiple LLM backbones, SpecAHD reduces held-out objective cost by up to 57.7% against the strongest competing AHD baseline and outperforms the per-instance baseline envelope on most public instances.
Jul 11, 2026

Sharper Analysis of Single-Loop Methods for Bilevel Optimization

Bilevel optimization underpins many machine learning applications, including hyperparameter optimization, meta-learning, neural architecture search, and reinforcement learning. While hypergradient-based methods have advanced significantly, a gap persists between theoretical guarantees and practical single-loop implementations required for efficiency. We bridge this gap by establishing sharper convergence results for single-loop approximate implicit differentiation (AID) and iterative differentiation (ITD) methods, leveraging our proposed analytical framework, decoupled norm analysis (DNA). For AID, we improve the convergence rate from O(κ6/K)\mathcal{O}(κ^6/K) to O(κ5/K)\mathcal{O}(κ^5/K), where κκ is the condition number of the inner-level problem. For ITD, we prove that the asymptotic error is O(κ2)\mathcal{O}(κ^2), exactly matching the known lower bound and improving upon the previous O(κ3)\mathcal{O}(κ^3) guarantee. Numerical experiments on synthetic and real tasks corroborate our theoretical findings.
Jul 6, 2026

Directly Optimizing Mean Demographic Parity for Nonlinear Regression

We focus on regression settings where the fairness goal is to equalize average predictions across values of a sensitive attribute, a criterion known as mean demographic parity. Directly optimizing this criterion is difficult because it depends on a conditional mean that is unknown and changes during training. Common dependence penalties and adversarial methods do not estimate this conditional mean; instead, they push predictions toward full independence. This stronger constraint can reduce accuracy even when average predictions are already equal. Existing conditional-mean methods are limited to linear predictors or low-dimensional sensitive attributes. We enable direct optimization of mean demographic parity using DPVar, a fairness measure defined as the variance of the conditional mean prediction. Because the conditional mean must be estimated as the predictor changes, optimizing DPVar leads to a functional bilevel problem. We develop two solvers: FBO, which uses a closed-form hypergradient, and an iterative-differentiation (ITD) solver that differentiates through updates of the conditional-mean estimator. Unlike previous conditional-mean methods, our approach applies to nonlinear predictors and high-dimensional continuous sensitive attributes. Across a semi-synthetic benchmark built from 21 tabular regression datasets and Communities & Crime data, FBO and ITD recover competitive or better accuracy-DPVar trade-offs than existing methods.
Jun 30, 2026

Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization

Cycle self-training (CST) breaks the shared classifier assumption of the standard self-training framework, which is effective for unsupervised domain adaptation and exploits unlabeled target data by training with target pseudo-labels. CST introduces a target classifier and employs an inner-outer loop updating strategy, addressing the issue of unreliable pseudo-labels and enabling pseudo-labels to generalize across domains. Despite its success in image classification, extending CST to object detection faces three main challenges. First, the upper bound of CST in object detection is constrained by three types of unreliable pseudo-labels, such as classification error alone, localization error alone, and their combination. Second, since object detection involves detecting multiple target objects, directly applying CST leads to training insta bility. Third, a wider numerical range of regression coordinates leads to exploding losses. To this end, we apply CST to both classification and regression and propose the Dual-Stream Bilevel-Cycle Optimization framework. Specifically, we construct CST upon Mean Teacher to prevent training instability and use extra normalization to map the regression bounding box into a standardized space, effectively addressing exploding losses. Also, we provide a theoretical derivation of the regression bound. Extensive experiments across four cross domain standard scenarios demonstrate that our framework achieves considerable results.
Jun 28, 2026

Bilevel Optimization for Neural Architecture Search

Bilevel optimization has become an influential and widely adopted framework for addressing hierarchical optimization problems in machine learning, providing an effective approach to modeling the interaction between two levels of optimization, with applications such as hyperparameter tuning, meta-learning, adversarial training, and data poisoning. Neural Architecture Search (NAS), a subfield of hyperparameter optimization, is a prime example of a bilevel optimization problem, with architecture parameters optimized at the outer-level and network weights optimized at the inner level. This paper presents a structured overview of NAS through the lens of bilevel optimization. We categorize existing NAS approaches into two main classes: sampling-based methods, which search optimal architectures using different architecture samplers, and bilevel theory-based methods, which solve the architecture search problem using bilevel optimization principles. We further highlight our current research direction, wherein the bilevel NAS formulation is addressed through an auxiliary mathematical programming framework. This framework enables the systematic integration of second-order information from the model's training loss function and ensures the optimality of the model parameters while modifying architecture parameters. By simultaneously updating the architecture and model parameters along their respective optimal descent directions derived from the auxiliary mathematical program, these methods achieve more principled and theoretically consistent results. The same auxiliary program can also be used for simultaneous hyperparameter and model fine-tuning. A comparative analysis shows that bilevel theory-based approaches generally outperform sampling-based methods, both in accuracy and efficiency.
Jun 23, 2026

Agentic AI for Bilevel Long-Term Optimization of Policy-Driven Physical Layer Systems

Network operators' changing policies, service requirements, and stringent real-time constraints render existing methods designed with fixed objectives and constraints ineffective. This paper presents Agentic long-term performance optimization (Agentic-LTPO), a nested bilevel optimization framework that can be applied to adaptive physical layer problem configuration. The key idea is to employ agentic AI to generate upper-level configurations in a bilevel optimization structure, where evolving operator policies, environment summaries, and historical experiences are translated into structured lower-level optimization problem configurations. The lower level solves the problems with updated configurations for real-time physical-layer decisions. Considering cell-free MIMO beamforming as a use case, we embody Agentic-LTPO by designing a new multi-agent decision process with retrieval-augmented experience-based verification in the upper level, together with a closed-form beamformer in the lower level. Experiments demonstrate that Agentic-LTPO exhibits strong adaptability to dynamic operator policies and effectively enhances the system's long-term performance by 57.2% compared to traditional methods.
Jun 22, 2026

Constrained Variable Projection for Structured Problems

Variable projection is a classical technique for separable nonlinear least-squares problems, in which variables that enter linearly are eliminated exactly, yielding a reduced nonlinear problem. By expressing this framework as a particular instance of a broader class of bilevel optimization problems, we develop a constrained variable-projection framework for data-science models, where the remaining variables are subject to convex constraints and the eliminated variables arise from a lower-level least-squares problem. In particular, by interpreting variable projection as a collapsed bilevel optimization problem, we derive exact reduced-gradient formulas compatible with automatic differentiation and propose a conditional-gradient algorithm for the resulting constrained reduced problem. We establish convergence guarantees under standard smoothness and compactness assumptions, and discuss extensions to structured lower-level variables. Numerical experiments on sparse autoencoding, dictionary learning, blind deconvolution, and few-shot learning suggest that the method can improve wall-clock efficiency and data efficiency relative to natural joint-optimization baselines.
Jun 21, 2026

Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation

Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed stochastic noise. Existing variance-reduction techniques typically rely on myopic magnitude checks, which fail to distinguish informative geometric signals from impulsive outliers. To resolve this, we propose RQ-TTSA (Robust Quantile-guided TTSA), a distribution-aware framework that leverages historical gradient buffers to estimate rolling quantiles for adaptive Huber-style clipping, effectively preserving local optimization geometry while strictly bounding effective variance. Theoretically, we provide a convergence analysis for quantile-guided TTSA under nonconvex-strongly convex assumptions with infinite-variance noise (p∈(1,2]p \in (1,2]), deriving a rate of O(T−p−13p−2)\mathcal{O}(T^{-\frac{p-1}{3p-2}}) that recovers optimal dependence on the heavy-tailed parameter. Empirically, across six diverse tasks, spanning heterogeneous vision benchmarks, dynamic games under momentum poisoning, and offline reinforcement learning, RQ-TTSA consistently outperforms state-of-the-art baselines by eliminating divergence spikes and ensuring stable convergence. Our method demonstrates significant robustness to hyperparameter variations and incurs negligible computational overhead (≈2.7%\approx 2.7\% increase), validating distribution-aware gradient control as a practical and necessary component for reliable bilevel learning.
Jun 21, 2026

Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization

Many central machine learning tasks, from entropy tuning in reinforcement learning to equilibrating generative adversarial networks, are fundamentally stochastic root-finding problems rather than loss minimization. Yet, they are frequently forced into a minimization framework via squared residuals, introducing a critical flaw we identify as the Variance Trap. Standard bilevel minimization algorithms require estimating hypergradients involving implicit Jacobians; in stochastic settings, these terms act as noise amplifiers, destabilizing convergence. We formalize Root-Finding Bilevel Optimization (RF-BO) as a distinct problem class that bypasses this pathology. We propose a Jacobian-free solution using Two-Time-Scale Stochastic Approximation (TTSA) that updates directly along the root error, structurally avoiding variance amplification. We provide the first non-asymptotic convergence guarantees for TTSA in this setting under Markovian noise. Extensive experiments demonstrate the decisive advantage of this paradigm: compared to squared-residual and implicit-gradient baselines, our framework achieves a 2.6% top-1 accuracy gain in SimCLR, 17×\times faster convergence in non-linear ODE control where baselines fail, significantly improved entropy stability in reinforcement learning, and an 11.1% quality improvement in generative modeling.
Jun 19, 2026

DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity

Decentralized bilevel optimization (DBO) provides a powerful framework for multi-agent systems to solve local bilevel tasks in a decentralized fashion without the need for a central server. However, most existing DBO methods rely on lower-level strong convexity (LLSC) to guarantee unique solutions and a well-defined hypergradient for stationarity measure, hindering their applicability in many practical scenarios not satisfying LLSC. To overcome this limitation, we introduce a new single-loop DBO algorithm called diminishing quadratically-regularized bilevel decentralized optimization (DUET), which eliminates the need for LLSC by introducing a diminishing quadratic regularization to the lower-level (LL) objective. We show that DUET achieves an iteration complexity of O(1/T1−5p−114τ)O(1/T^{1-5p-\frac{11}{4}τ}) for approximate KKT-stationary point convergence under relaxed assumptions, where pp and ττ are control parameters for LL learning rate and averaging, respectively. In addition, our DUET algorithm incorporates gradient tracking to address data heterogeneity, a key challenge in DBO settings. To the best of our knowledge, this is the first work to tackle DBO without LLSC under decentralized settings with data heterogeneity. Numerical experiments validate the theoretical findings and demonstrate the practical effectiveness of our proposed algorithms.
Jun 18, 2026

Federated Bilevel Performative Prediction

Federated bilevel optimization is widely used for nested learning problems across distributed clients, such as federated hyperparameter tuning and meta-learning under privacy and communication constraints. Most existing formulations assume fixed client data distributions, which can be violated by performativity, where deployed decisions reshape client behavior and data collection, inducing client-specific, decision-dependent distribution shift. We study federated bilevel performative prediction, where both upper-level (UL) and lower-level (LL) objectives are evaluated under client-dependent, decision-dependent distributions. We formalize the federated bilevel performatively stable (FBPS) point under a decoupled-risk perspective and provide sufficient conditions for its existence and uniqueness. We then develop two federated methods to compute the FBPS solution: FBi-RRM, which converges linearly under a contraction condition, and FBi-SGD, a communication-efficient stochastic method based on federated hypergradient estimation with convergence guarantees under diminishing step sizes when sensitivities are sufficiently small. Experiments on strategic regression and meta strategic classification validate the predicted stability thresholds and demonstrate improved meta-generalization over non-performative baselines, and CNN-based classification further demonstrates the practical effectiveness of the proposed methods in nonconvex neural network settings.
Jun 17, 2026

BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training

As Large Language Model (LLM) datasets scale to trillions of tokens, data selection has emerged as a critical frontier to filter out uninformative noise and construct adaptive learning trajectories. Beyond static heuristic filtering, advanced data selection methods for LLM training largely follow two paradigms, each with fundamental limitations. Influence-based methods provide principled bi-level objectives but require intractable inverse-Hessian computations, while excess-loss methods are computationally efficient but rely on a static reference model that becomes misaligned with the evolving proxy model during training. We propose BLADE (Bi-Level Adaptive Data sElection), a Hessian-free framework for data selection. BLADE reformulates the bi-level optimization problem underlying influence-based methods as a penalized single-level objective via Lagrange multipliers, avoiding inverse-Hessian computation while revealing a principled connection to excess-loss based data selection. The resulting objective recovers an excess-loss form but replaces the static reference model with a dynamic one that stays synchronized with training. Theoretically, we prove that this penalized formulation guarantees first-order convergence. For efficient online batch selection, we instantiate BLADE as a memoryless randomized block-coordinate Frank-Wolfe algorithm. Extensive experiments show that BLADE consistently outperforms state-of-the-art data selection baselines, providing a practical recipe for LLM training.
Jun 11, 2026

Mixed-Categorical Black-Box Optimization via Information-Geometric Bilevel Decomposition

Mixed categorical-continuous optimization arises in many practical domains, yet remains challenging. In the black-box setting, evolution strategy-based approaches have shown promise in extending the efficiency and robustness of the CMA-ES to mixed-variable spaces. However, these methods exhibit worsened performance when strong categorical-continuous interactions are present, as their underlying search distributions assume independence between categorical and continuous variables. To address this limitation, we propose a bilevel optimization framework that explicitly captures such interactions by optimizing over categorical variables in an outer loop, and over continuous variables conditioned on each categorical configuration in an inner loop. We formulate each level of the bilevel problem as a stochastic relaxation under information-geometric optimization. To mitigate the high computational cost inherent to bilevel optimization, we introduce a warm-starting strategy that accelerates the lower-level search by selecting the best among multiple cached configurations and updating the cache after each iteration. Experimental results on binary-continuous domain demonstrate that the proposed method outperforms existing state-of-the-art approaches in interaction-handling capability while also being more computationally efficient across benchmarks encompassing both previously reported and newly proposed types of interaction.
Jun 9, 2026

Gradient based Bilevel for Inverse Optimal Control, a Riemannian approach

Inverse Optimal Control (IOC) aims to recover the cost function that explains observed trajectories as solutions of an optimal control problem. Classical IOC formulations rely on bilevel optimization, which repeatedly solves a nested optimal control problem and quickly becomes computationally prohibitive for realistic systems. Recent projection-based approaches offer a promising alternative but suffer from numerical instability when solved with gradient-based methods due to violations of standard constraint qualifications. In this paper, we show that these difficulties stem from the geometric structure of the IOC feasible set. We demonstrate that the set of trajectories satisfying the optimality conditions naturally forms a manifold and reformulate IOC as an optimization problem on this manifold. Based on this insight, we propose a Riemannian Inverse Optimal Control (RIOC) method that projects observed trajectories onto the manifold of optimal solutions while preserving feasibility by construction. Experiments on real human arm trajectories show that the proposed method achieves comparable or better reconstruction accuracy than classical bilevel IOC while reducing computation time by about a factor of four. These results highlight the potential of geometric optimization methods to improve the scalability and reliability of IOC for robotics and human motion analysis.
Jun 3, 2026

TANDEM: Bi-Level Data Mixture Optimization with Twin Networks

The capabilities of large language models (LLMs) significantly depend on training data drawn from various domains. Optimizing domain-specific mixture ratios can be modeled as a bi-level optimization problem, which we simplify into a single-level penalized form and solve with twin networks: a proxy model trained on primary data and a dynamically updated reference model trained with additional data. Our proposed method, Twin Networks for bi-level DatA mixturE optiMization (TANDEM), measures the data efficacy through the difference between the twin models and up-weights domains that benefit more from the additional data. TANDEM provides theoretical guarantees and wider applicability, compared to prior approaches. Furthermore, our bi-level perspective suggests new settings to study domain reweighting such as data-restricted scenarios and supervised fine-tuning, where optimized mixture ratios significantly improve the performance. Extensive experiments validate TANDEM's effectiveness in all scenarios.
May 30, 2026

On the Difficulty of Learning a Meta-network for Training Data Selection

Synthetic data are increasingly used to train neural networks, yet distributional mismatch with real data limits their effectiveness when used indiscriminately. A common strategy is to learn data weights via bi-level optimization, which we refer to as Meta-learning for Training-data Selection (MTS). Interestingly, in practice, MTS often performs below expectation. We identify two obstacles in properly training MTS: a poor gradient signal-to-noise ratio (GSNR), which causes optimization difficulties, and lack of informative features that correlates with data quality. We present a mathematical analysis of MTS, which reveals the dynamics of normalized data weights and the relation between disparate data quality and poor GSNR. The analysis suggests a a simple yet effective solution: increasing the batch size. Further, we propose a set of informative features that capture the positions of training data in their distributions and training dynamics. Experiments across four benchmarks show consistent improvements, achieving average gains of 5.49% over training without selection and 2.89% over the strongest baseline.
May 29, 2026

S3^3LDBO: A Snapshot Single-Loop Algorithm for Decentralized Bilevel Optimization

Networked AI systems increasingly rely on multiple agents that collaboratively learn and adapt models over communication networks. In such systems, bilevel formulations naturally arise in hyperparameter optimization, data cleaning, and meta-learning, but the repeated evaluation of gradients, Jacobians, and Hessians can impose a substantial computational burden on individual agents. To address this challenge, we propose Snapshot-SLDBO (S3^3LDBO), an efficient single-loop decentralized bilevel optimization algorithm that enables agents to intermittently skip expensive derivative evaluations through a snapshot mechanism. This mechanism can be interpreted as an autonomous computation-adaptation strategy for networked AI, where agents selectively perform costly local updates while maintaining global collaborative learning. We establish the ergodic iteration complexity and the high probability nonergodic iteration complexity of the proposed algorithm within a deterministic setting. Experimental results on hyperparameter optimization with synthetic and MNIST datasets, data hyper-cleaning on Fashion-MNIST, and decentralized meta-learning on miniImageNet demonstrate that the proposed algorithm improves computational efficiency while maintaining competitive learning performance.
May 26, 2026

Adversarial Training for Robust Coverage Network under Worst-case Facility Losses

The Maximal Covering Location-Interdiction Problem (MCLIP) is a classic bi-level optimization problem, which is fundamental to resilient infrastructure planning yet remains computationally intractable. Specifically, the upper level determines facility locations to maximize coverage, while the lower level executes worst-case interdiction to minimize the coverage. The strong coupling between the upper and lower levels, combined with their respective high combinatorial complexity, renders traditional methods ineffective. To bridge this gap, we propose a Dual-Agent Deep Reinforcement Learning (DADRL) framework based on adversarial learning, comprising a location agent corresponding to the upper level and an interdiction agent corresponding to the lower level. Our contributions are threefold: (1) The location agent is trained simultaneously against an evolving interdiction agent, making it effectively capture the dynamic competitive interplay between the upper and lower levels; (2) To fully exploit the learned capabilities of the interdiction agent, we propose a Surrogate-based Ensemble Inference Strategy that utilizes the trained interdiction agent as a high-fidelity surrogate to guide the decisions of location agent; (3) Extensive experiments on synthetic and real-world datasets demonstrate that our approach achieves superior computational efficiency while maintaining highly competitive solution quality compared to other baselines. Furthermore, our DADRL framework is model-agnostic to network structures, while its underlying adversarial learning paradigm demonstrates strong potential for solving other bi-level optimization problems.
May 26, 2026

Bilevel Optimization over Saddle Points of Zero-Sum Markov Games

Reinforcement learning (RL) often has a hierarchical structure, where an upper-level (UL) learner selects model parameters and a lower-level (LL) decision-making process responds, naturally leading to a bilevel optimization problem. Most existing bilevel RL methods assume a single-policy LL Markov decision process (MDP), and therefore fail to capture competitive structures arising in applications such as incentive design, where multiple policies interact. We study bilevel optimization problems in which the LL problem is a regularized min-max zero-sum Markov game and the UL objective is optimized through the saddle-point equilibrium induced by the LL game. In this work, we propose penalty-augmented Nikaido-Isoda descent-ascent (PANDA), a penalty-based first-order policy-gradient method based on the Nikaido-Isoda function. By exploiting the min-max game structure, PANDA avoids computing UL hypergradients and does not require second-order information. We prove that PANDA converges to stationary points without convexity assumptions on either the UL or LL objectives. Moreover, PANDA reaches an εε-stationary point in O~(ε−1)\tilde{\mathcal{O}}(ε^{-1}) iterations with sample complexity O~(ε−3)\tilde{\mathcal{O}}(ε^{-3}), matching the best-known rates for bilevel RL with single-policy LL MDPs. Experiments demonstrate the superior performance of PANDA over closely related baselines.
May 23, 2026

Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning

While LLMs excel at single-turn generation, they struggle with long-horizon, multi-turn interactions. Offline reinforcement learning (RL) offers a scalable approach, yet its performance hinges on the availability and quality of multi-turn trajectory data. A common remedy is to augment training with synthetic trajectories generated by LLMs or simulators, but synthetic data is highly heterogeneous in quality, and naively treating all trajectories as equally informative can degrade performance. We propose BOOST, a bilevel optimization framework where the inner level trains the LLM on reweighted data and the outer level trains a lightweight reweighting head on held-out real validation tasks, assigning continuous trajectory-level weights without requiring an external judge. To ground this approach, we derive a PAC-Bayesian bound revealing a three-way trade-off: synthetic data increases diversity but risks task-shift, while concentrating weight on high-quality trajectories improves empirical performance at the cost of effective sample size. Empirically, our method consistently outperforms multiple baselines. Analysis reveals it upweights synthetic trajectories that align with the real data distribution and exhibit higher qualitative merit.
May 23, 2026

RL with Learnable Textual Feedback: A Bilevel Approach

Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing line of work on RL with textual feedback, where a critic model generates natural language feedback to guide a reasoning model (the actor), augmenting scalar rewards with richer learning signals. However, existing methods typically treat feedback as fixed or auxiliary, which misses a key property: feedback should not merely be correct, but should improve the policy (actor model) when provided in context. This motivates a paradigm of learnable textual feedback for RL. Yet the learnability and usefulness of feedback depend on the policy's ability to learn from it, making RL with learnable feedback an inherently bilevel problem. We formalize this coupling as a Stackelberg bilevel program and derive Bilevel Natural Language Actor-Critic (Bi-NAC), which jointly trains a critic to generate reward-improving feedback and an actor to exploit it. Across MATH-500, MBPP, and GPQA, Bi-NAC improves sample and parameter efficiency over RL and fixed-critic baselines: our 2B model outperforms the 3B GRPO baseline, achieving 46.6% versus 41.4% on MATH-500, while our 6B model surpasses the 7B GRPO baseline, achieving 49.3% versus 43.6% on GPQA.
May 20, 2026

Parametric Rates for Nonparametric Conditional-Moment Bilevel Optimization

We study functional bilevel optimization with conditional moments, where plug-in hypergradients can inherit first-order errors from nonparametrically learned conditional expectations. We introduce OBiGrad, an orthogonalized hypergradient estimator whose bias is a product of nuisance errors. Under our regression and complexity conditions, projected gradient descent with the direct plug-in hypergradient yields expected stationarity error O(T−1/2+n−1/2+n−ν/b)O(T^{-1/2}+n^{-1/2}+n^{-ν/b}) for the best iterate, whereas OBiGrad achieves O(T−1/2+n−1/2+n−2ν/b)O(T^{-1/2}+n^{-1/2}+n^{-2ν/b}), where b=ν(2+p)+γb=ν(2+p)+γ combines the approximation and complexity exponents. Consequently, when ν(2−p)≥γν(2-p)\geγ, OBiGrad attains the parametric statistical rate O(T−1/2+n−1/2)O(T^{-1/2}+n^{-1/2}), improving the sufficient sample-size bound relative to the direct plug-in bound for a fixed iteration budget. We illustrate these gains on instrumental-variable and fitted-Q-regression problems, examining stationary-point estimation, returned population stationarity, and regularization sensitivity.