paper-with-me

Papers

Differentiable Convex Optimization Layers in Neural Architectures: Foundations and Perspectives

2024-12-30 · Calder Katyal

The integration of optimization problems within neural network architectures represents a fundamental shift from traditional approaches to handling constraints in deep learning. While it is long known that neural networks can incorporate soft constraints with techniques such as regularization, strict adherence to hard constraints is generally more difficult. A recent advance in this field, however, has addressed this problem by enabling the direct embedding of optimization layers as differentiable components within deep networks. This paper surveys the evolution and current state of this approach, from early implementations limited to quadratic programming, to more recent frameworks supporting general convex optimization problems. We provide a comprehensive review of the background, theoretical foundations, and emerging applications of this technology. Our analysis includes detailed mathematical proofs and an examination of various use cases that demonstrate the potential of this hybrid approach. This work synthesizes developments at the intersection of optimization theory and deep learning, offering insights into both current capabilities and future research directions in this rapidly evolving field.

📄 PDF Abstract BibTeX arXiv:2412.20679

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Proofs

Similar Papers 제목 키워드 기반

Differentiable Convex Optimization Layers

2019-10-28 · NeurIPS 2019 12 · Akshay Agrawal, Brandon Amos, Shane Barratt, Stephen Boyd 외

Recent work has shown how to embed differentiable optimization problems (that is, problems whose solutions can be backpropagated through) as layers within deep learning architectures. This method provides a useful induct…

Inductive Bias

DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers

2026-05-28 · Shraman Pal, Can Li arxiv

Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these problems are often accompanied by rich domain …

Convex Optimization with an Interpolation-based Projection and its Application to Deep Learning

2020-11-13 · Riad Akrour, Asma Atamna, Jan Peters

Convex optimizers have known many applications as differentiable layers within deep neural architectures. One application of these convex layers is to project points into a convex set. However, both forward and backward …

OptNet: Differentiable Optimization as a Layer in Neural Networks

2017-03-01 · ICML 2017 8 · Brandon Amos, J. Zico Kolter

This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks. These lay…

Bilevel OptimizationGPU

BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning

2024-11-28 · Jianming Pan, Zeqi Ye, Xiao Yang, Xu Yang 외

Data-driven decision-making processes increasingly utilize end-to-end learnable deep neural networks to render final decisions. Sometimes, the output of the forward functions in certain layers is determined by the soluti…