The reviewed record of science sign in
Pith

arxiv: 2504.01212 · v1 · pith:DDOHM55X · submitted 2025-04-01 · cs.LG · cs.MS

Cooper: A Library for Constrained Optimization in Deep Learning

Jose Gallego-Posada , Juan Ramirez , Meraj Hashemizadeh , Simon Lacoste-Julien This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:DDOHM55Xrecord.jsonopen to challenge →

classification cs.LG cs.MS
keywords cooperconstraineddeeplearningoptimizationalgorithmsalthoughapplications
0
0 comments X
read the original abstract

Cooper is an open-source package for solving constrained optimization problems involving deep learning models. Cooper implements several Lagrangian-based first-order update schemes, making it easy to combine constrained optimization algorithms with high-level features of PyTorch such as automatic differentiation, and specialized deep learning architectures and optimizers. Although Cooper is specifically designed for deep learning applications where gradients are estimated based on mini-batches, it is suitable for general non-convex continuous constrained optimization. Cooper's source code is available at https://github.com/cooper-org/cooper.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization

    cs.LG 2026-06 unverdicted novelty 7.0

    PCD is a new gradient-based optimizer for hierarchical multi-objective problems that prioritizes primary descent with minimal controlled distortion for secondary objectives via a single tau parameter.

  2. How pore-scale disorder controls fluid stretching in porous media

    physics.flu-dyn 2026-04 unverdicted novelty 7.0

    Pore-scale disorder accelerates fluid stretching in porous media, producing quadratic time growth and faster mixing than the linear growth seen in ordered structures.

  3. Unsupervised Causal Abstractions Discovery

    cs.LG 2026-06 unverdicted novelty 6.0

    Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.

  4. Position: Adopt Constraints Over Fixed Penalties in Deep Learning

    cs.LG 2025-05 accept novelty 4.0

    Fixed penalty methods in deep learning do not reliably solve problems with hard non-negotiable constraints, so the constrained formulation should be the starting point instead.