Skip to content
Preprint

Residual-Controlled Douglas--Rachford Splitting for Differentiable Solver Layers

Aug 2026 · 1 citation · 29 references
Mathematics

TL;DR

Residual-Controlled Douglas--Rachford Splitting (RCDRS), a differentiable solver layer for conic linear programs that treats an unrolled solver as a feedback-controlled dynamical system, where a causal controller adapts the relaxation and objective-drive parameters while preserving the projection-splitting structure of Douglas--Rachford splitting.

Abstract

Differentiable solver layers embed constrained optimization into end-to-end learning systems, but fixed-depth unrolling must trade off solution quality, feasibility, and computational budget. We propose Residual-Controlled Douglas--Rachford Splitting (RCDRS), a differentiable solver layer for conic linear programs. RCDRS treats an unrolled solver as a feedback-controlled dynamical system, where a causal controller adapts the relaxation and objective-drive parameters while preserving the projection-splitting structure of Douglas--Rachford splitting. Theoretically, we show that each fixed admissible block remains an averaged relaxed DRS operator and admits finite-step fixed-point residual bounds. We further analyze safeguarded time-varying rollouts as summable perturbations of a limiting averaged operator, and recover terminal primal-dual diagnostics from the final splitting state. Experiments on mixed-cone benchmarks and engineering applications show that RCDRS improves solution quality, feasibility and downstream decision performance. The code is available at https://anonymous.4open.science/r/RC-DRS-180C/.

View source

Similar papers

#machine learning Preprint Sep 2026

dOPT: Differentiating Conic Optimization via Geometric Reduction

Optimization layers enable the incorporation of structured constraints and decision problems into learning systems. Training such systems requires differentiating through the embedded optimization problem, which can be challenging for general conic programs. We introduce dOPT, a solver-agnostic framework that, rather t...

Feng-Yu Yang, Connor W. Magoon, Tyler Watts et al. · 0 citations
#machine learning Preprint Sep 2026

Learned Preconditioning for a Primal-Dual Interior-Point Method

Interior-point methods (IPMs) are among the most widely used algorithms for constrained optimization, yet their Newton-based search directions require costly second-order information and large linear-system solves. Learning to optimize offers cheaper updates learned from data, but the singular behavior of logarithmic b...

A. Madabhushi, Jia-Lin Liu, Min-Xin Zhang · 0 citations

lapanda: A Matrix-Free Differentiable Solver for Nonconvex Constrained Optimization Layers

This work reformulates the problem to a sequence of augmented Lagrangian subproblems, each handled by a first-order inner solver through a proximal averaged quasi-Newton algorithm with adaptive linesearch, thus enabling efficient forward optimization.

Yuan-Kun Chen, Zi-Fei Nie, Kang-Yu Lin et al. · 0 citations
#artificial intelligence Preprint Oct 2026

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

GALLOP is introduced, which uses reinforcement learning to jointly learn continuous algorithm parameters and discrete restart decisions without differentiating through the solver, and achieves up to a speedup in algorithm wall-clock time over MPAX.

Jinhwan Sul, Alex Oshin, Evangelos A. Theodorou · 0 citations
#artificial intelligence Preprint Sep 2026

Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers

Neural operators provide fast surrogates for time-dependent PDEs, but autoregressive deployment creates a refinement-allocation problem: prediction errors vary over space and time, while only a finite number of local corrections can be committed along a trajectory. We formulate this as budgeted adaptive neural-operator...

An-Ge Tong · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.