REVIEW 4 cited by
Cooper: A Library for Constrained Optimization in Deep Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Cooper: A Library for Constrained Optimization in Deep Learning
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.
Forward citations
Cited by 4 Pith papers
-
Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization
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.
-
How pore-scale disorder controls fluid stretching in porous media
Pore-scale disorder accelerates fluid stretching in porous media, producing quadratic time growth and faster mixing than the linear growth seen in ordered structures.
-
Unsupervised Causal Abstractions Discovery
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.
-
Position: Adopt Constraints Over Fixed Penalties in Deep Learning
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.