Reinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programming

arXiv:2610.01546 · math.OC, cs.AI, cs.LG · Submitted 2026-10-01 · Read on arXiv

math.OC, cs.AI, cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: 35 pages, 4 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces
• Discrete and Continuous Action Representation for Practical RL in Video Games
• A generic adaptive restart scheme with applications to saddle point algorithms
• Restarted Halpern PDHG for Linear Programming
• cuPDLP-C: A Strengthened Implementation of cuPDLP for Linear Programming by C language
• MPAX: Mathematical Programming in JAX
• cuPDLPx: A Further Enhanced GPU-Based First-Order Solver for Linear Programming
• Learning to accelerate Krasnosel'skii-Mann fixed-point iterations with guarantees
• Scalable Deep Unfolding of Conic Optimizers
• Proximal Policy Optimization Algorithms
• Neural Fixed-Point Acceleration for Convex Optimization
• Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space
• Anderson Accelerated Primal-Dual Hybrid Gradient for solving LP

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Second-Order Optimization with Asynchronous Curvature
• Online Control via Counterfactual Tracking
• Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability