Learning to Optimize

Ask about this topic

Overview

Learning to Optimize studies how data can improve the algorithms and decisions used to solve optimization problems, especially when similar problems recur or standard solvers are costly. Approaches include meta-learning and reinforcement learning for update rules and optimizer selection, unrolled or differentiable methods such as learned ADMM, and learned heuristics or warm starts for mixed-integer and other solvers. These methods are used in settings ranging from neural-network training and black-box search to scheduling, power systems, and model predictive control, with work increasingly combining fast learned predictions with exact optimization or explicit feasibility checks. A central tension is whether methods trained on particular instances can generalize reliably to new problems while preserving solution quality, constraint satisfaction, and the computational guarantees of classical solvers.

Latest papers

CardsList

139 papers27 papers in the last four weeks, up 125% on the four weeks before. 0.2% of all new papers.

  1. OptiRoulette Optimizer: A New Stochastic Meta-Optimizer for up to 5.3x Faster Convergence

    Feb 20, 2026Stamatis MastromichalakisNeural Network OptimizationStochastic Optimization

    Independent Researcher, tmnetworks.gr

  2. POP: Prior-Fitted First-Order Optimization Policies

    Feb 17, 2026Jan Kobiolka, Christian Frey, Gresa Shala +3Learning to OptimizeAdaptive Gradient Methods

    Department of Computer Science University of Technology Nuremberg Germany · Department of Computer Science Albert Ludwig University of Freiburg Germany · Faculty of Natural Sciences University of Elbasan Albania

  3. Learning to Discover Iterative Spectral Algorithms

    Feb 10, 2026Zihang Liu, Oleg Balabanov, Yaoqing Yang +1Automated Algorithm DiscoveryLearning to Optimize

    1International Computer Science Institute · University of California, Berkeley · 4Lawrence Berkeley National Laboratory +1

  4. Meta-Learning-Assisted Constraint Relaxation for Constrained Black-Box Optimization

    Jan 31, 2026Sijie Ma, Zeyuan Ma, Yue-Jiao Gong +1Black-Box OptimizationLearning to Optimize

    Hong Kong Polytechnic University · South China Normal University · South China University of Technology

  5. Unrolled Neural Networks for Constrained Optimization

    Jan 24, 2026Samar Hadou, Alejandro RibeiroConstrained OptimizationLearning to Optimize

    Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA 19104 USA

  6. Learning to Optimize by Differentiable Programming

    Jan 23, 2026Liping Tao, Xindi Tong, Chee Wei TanPrimal-Dual OptimizationLearning to Optimize

    Nanyang Technological University, Singapore · Nanyang Technological University, Singapore, Singapore

  7. Learning to accelerate Krasnosel'skii-Mann fixed-point iterations with guarantees

    Jan 12, 2026Andrea Martin, Giuseppe BelgioiosoOptimization Convergence AnalysisLearning to Optimize

    Division of Decision and Control Systems, KTH Royal Institute of Technology, and Digital Futures, SE-100 44 Stockholm, Sweden

  8. 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 LearningQuantum 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

  9. Machine Learning Guided Optimal Transmission Switching to Mitigate Wildfire Ignition Risk

    Oct 29, 2025Weimin Huang, Ryan Piansky, Bistra Dilkina +1Mixed-Integer Linear ProgrammingLearning 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

  10. Inverse Mixed-Integer Programming: Learning Constraints then Objective Functions

    Oct 6, 2025Akira KitaokaMixed-Integer Linear ProgrammingLearning to Optimize

  11. L-SR1: Learned Symmetric-Rank-One Preconditioning

    Aug 17, 2025Gal Lifshitz, Shahar Zuler, Ori Fouks +1Learning to OptimizeSecond-Order Optimization

    Tel Aviv University, Tel Aviv, Israel.

  12. Direct Regret Optimization in Bayesian Optimization

    Jul 9, 2025Fengxue Zhang, Yuxin ChenBayesian OptimizationLearning to Optimize

    Department of Computer Science University of Chicago Chicago, IL 60637

  13. Accelerating Optimization via Differentiable Stopping Time

    May 28, 2025Zhonglin Xie, Yiman Fong, Haoran Yuan +1Differentiable OptimizationHyperparameter Optimization

    Beijing International Center for Mathematical Research, Peking University · Department of Industrial Engineering, Tsinghua University · School of Mathematics Science, Peking University

  14. Deep Learning Warm Starts for Trajectory Optimization on the International Space Station

    May 8, 2025Somrita Banerjee, Abhishek Cauligi, Marco PavoneTrajectory OptimizationLearning to Optimize

    Somrita Banerjee is a Machine Learning Researcher at Apple. Work completed during PhD at Stanford University, Stanford, CA 94305, USA. · Abhishek Cauligi is an Assistant Professor in the Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA. · Marco Pavone is an Associate Professor in the Department of Aeronautics and Astronautics, Stanford University, Stanford, CA 94305, USA.

  15. Sufficient Decision Proxies for Decision-Focused Learning

    May 6, 2025Noah Schutte, Grigorii Veviurko, Krzysztof Postek +1Stochastic OptimizationLearning to Optimize

    Delft University of Technology · Independent Researcher

  16. Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networks

    Mar 31, 2025Fangtong Zhou, Xiaorui Liu, Ruozhou Yu +1Graph Neural NetworksLearning 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

  17. Simulating, Fast and Slow: Learning Policies for Black-Box Optimization

    Jun 6, 2024Tim Bakker, Fabio Valerio Massoli, Thomas Hehn +2Black-Box OptimizationLearning to Optimize

    University of Amsterdam § · Qualcomm AI Research‡

  18. MEGO: Learning Mixture-of-Experts for General-Purpose Binary Optimization

    May 29, 2024Shengcai Liu, Zhiyuan Wang, Yew-Soon Ong +2Black-Box OptimizationMixture 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

  19. LOOP-MAC: Learning-Based Multi-Agent Coordination with Guaranteed Local Feasibility in a Virtual Power Plant

    Oct 27, 2023Meiyi Li, Lucas Ruda, Javad MohammadiMulti-Agent CoordinationPower Systems