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

All topics

Learning Over-Relaxation Policies for ADMM with Convergence Guarantees
Apr 29, 2026Junan Lin, Paul J. Goulart, Luca FurieriLearning to Optimize Alternating Direction Method of Multipliers
Department of Engineering Science, University of Oxford, OX1 3PJ Oxford, UK
Accelerating Regularized Attention Kernel Regression for Spectrum Cartography
Apr 28, 2026Liping Tao, Chee Wei TanLearning to Optimize
College of Computing and Data Science, Nanyang Technological University, Singapore 639798
Transferable SCF-Acceleration through Solver-Aligned Initialization Learning
Apr 23, 2026Eike S. Eberhard, Viktor Kotsev, Timm Güthle +1Quantum Chemistry Learning to Optimize
1Technical University of Munich (TUM) · 2Munich Data Science Institute (MDSI) · 3Munich Center for Machine Learning (MCML)
Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
Apr 22, 2026Shan He, Runze Wang, Zhuoyun Du +4Multi-Agent System Optimization Learning to Optimize
Future Living Lab of Alibaba
Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints
Apr 21, 2026Konstantinos Ziliaskopoulos, Alexander VinelPredict-Then-Optimize Learning to Optimize
Auburn University
RELOAD: A Robust and Efficient Learned Query Optimizer for Database Systems
Apr 16, 2026Seokwon Lee, Jaeyoung Sim, Sihyun Kim +3Learning to Optimize Robust RL
Yonsei University BDAI Lab, Seoul 03722, South Korea · Microsoft Gray Systems Lab, Redmond, USA
HUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization
Apr 14, 2026Trinh Tran, Binh Nguyen, Truong X. NghiemLearning to Optimize Alternating Direction Method of Multipliers
Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL 32816, USA
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
Apr 13, 2026I. Esra BuyuktahtakinReinforcement Learning Predict-Then-Optimize
Grado Department of Industrial and Systems Engineering, Virginia Tech Blacksburg, VA 24061, USA
One-Shot Localisation of the Global Minimum of a Noisy One-Dimensional Function: An Iterative Neural Minimizer Compared with Set Transformers and Classical Estimators
Apr 4, 2026Qusay Muzaffar, David Levin, Michael WermanBlack-Box Optimization Zeroth-Order Optimization
Department of Computer Science, The Hebrew University of Jerusalem, Israel · Department of Applied Mathematics, Tel Aviv University, Israel
When does learning pay off? A study on DRL-based dynamic algorithm configuration for carbon-aware scheduling
Apr 2, 2026Andrea Mencaroni, Robbert Reijnen, Yingqian Zhang +1RL Control Learning to Optimize
Department of Industrial Systems Engineering and Product Design, Ghent University, Ghent, Belgium · Industrial Systems Engineering (ISyE), Flanders Make, Kortrijk, Belgium · Eindhoven Artificial Intelligence Systems Institute, Eindhoven University of Technology, The Netherlands +1
Learning to Discover Iterative Spectral Algorithms
Feb 10, 2026Zihang Liu, Oleg Balabanov, Yaoqing Yang +1Automated Algorithm Discovery Learning to Optimize
1International Computer Science Institute · University of California, Berkeley · 4Lawrence Berkeley National Laboratory +1
Meta-Learning-Assisted Constraint Relaxation for Constrained Black-Box Optimization
Jan 31, 2026Sijie Ma, Zeyuan Ma, Yue-Jiao Gong +1Black-Box Optimization Learning to Optimize
Hong Kong Polytechnic University · South China Normal University · South China University of Technology
Learning to Optimize by Differentiable Programming
Jan 23, 2026Liping Tao, Xindi Tong, Chee Wei TanPrimal-Dual Optimization Learning to Optimize
Nanyang Technological University, Singapore · Nanyang Technological University, Singapore, Singapore
Reinforcement Learning to Initialize Newton-Raphson for AC Power Flow with Quantum Annealing-Based Environment Updates
Nov 25, 2025Zeynab Kaseb, Matthias Moller, Lindsay Spoor +4Reinforcement Learning Quantum Annealing
Electrical Sustainable Energy, Delft University of Technology, P.O. Box 5031, 2600 GA Delft, The Netherlands. · Applied Mathematics, Delft University of Technology, P.O. Box 5031, 2600 GA Delft, The Netherlands. · Leiden Institute of Advanced Computer Science, Leiden University, P.O. Box 9512, 2300 RA Leiden, The Netherlands. +3
Machine Learning Guided Optimal Transmission Switching to Mitigate Wildfire Ignition Risk
Oct 29, 2025Weimin Huang, Ryan Piansky, Bistra Dilkina +1Mixed-Integer Linear Programming Learning to Optimize
Department of Computer Science University of Southern California Los Angeles, CA, USA · School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta, GA, USA
Inverse Mixed-Integer Programming: Learning Constraints then Objective Functions
Oct 6, 2025Akira KitaokaMixed-Integer Linear Programming Learning to Optimize
L-SR1: Learned Symmetric-Rank-One Preconditioning
Aug 17, 2025Gal Lifshitz, Shahar Zuler, Ori Fouks +1Learning to Optimize Second-Order Optimization
Tel Aviv University, Tel Aviv, Israel.
Direct Regret Optimization in Bayesian Optimization
Jul 9, 2025Fengxue Zhang, Yuxin ChenBayesian Optimization Learning to Optimize
Department of Computer Science University of Chicago Chicago, IL 60637
Sufficient Decision Proxies for Decision-Focused Learning
May 6, 2025Noah Schutte, Grigorii Veviurko, Krzysztof Postek +1Stochastic Optimization Learning to Optimize
Delft University of Technology · Independent Researcher
Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networks
Mar 31, 2025Fangtong Zhou, Xiaorui Liu, Ruozhou Yu +1Graph Neural Networks Learning to Optimize
Department of Computer Science, North Carolina State University, Raleigh, NC, 27606, USA · School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, 85287, USA
MEGO: Learning Mixture-of-Experts for General-Purpose Binary Optimization
May 29, 2024Shengcai Liu, Zhiyuan Wang, Yew-Soon Ong +2Black-Box Optimization Mixture of Experts
Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China · College of Computing & Data Science, Nanyang Technological University, Singapore 639798 · School of Data Science, Lingnan University, Hong Kong, China
Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates
Date pendingSaumya Goyal, Rohith Rongali, Ritabrata Ray +1Meta-Learning Gradient Descent
Machine Learning Department, Carnegie Mellon University · Electrical and Computer Engineering Department, Carnegie Mellon University.
Code-to-Harness: Distilling Black-Box Optimizers from Self-Play
Date pendingYi Wu, Zheng Ren, Zhiyu Hu +8Black-Box Optimization Large Language Model-Guided Optimization
Google Mountain View, USA

Apr 29, 2026, math.OCJ/K move · Enter open · S save

Learning Over-Relaxation Policies for ADMM with Convergence Guarantees

Junan Lin, Paul J. Goulart, Luca Furieri

Department of Engineering Science, University of Oxford, OX1 3PJ Oxford, UK

Learning to Optimize Alternating Direction Method of Multipliers Constrained Optimization

Open paper AskPDF arXiv

The Alternating Direction Method of Multipliers (ADMM) is a widely used method for structured convex optimization, and its practical performance depends strongly on the choice of penalty and relaxation parameters. Motivated by settings such as Model Predictive Control (MPC), where one repeatedly solves related optimization problems with fixed structure and changing parameter values, we propose learning online updates of the relaxation parameter to improve average performance on problem classes of interest, while guaranteeing that asymptotic convergence is not compromised for the worst-case realization of such problems. This choice is computationally attractive in the Operator Splitting Quadratic Program (OSQP)-like architectures, since adapting relaxation does not trigger the matrix refactorizations associated with penalty updates. We establish convergence guarantees for ADMM with time-varying penalty and relaxation parameters under mild assumptions, and show on benchmark quadratic programs that the resulting learned policies improve both iteration count and wall-clock time on average over baseline OSQP.

Momentum

Related topics

Latest papers 83