paper-with-me

홈 › Papers

Homotopy Relaxation Training Algorithms for Infinite-Width Two-Layer ReLU Neural Networks

2023-09-26 · Yahong Yang, Qipin Chen, Wenrui Hao

In this paper, we present a novel training approach called the Homotopy Relaxation Training Algorithm (HRTA), aimed at accelerating the training process in contrast to traditional methods. Our algorithm incorporates two key mechanisms: one involves building a homotopy activation function that seamlessly connects the linear activation function with the ReLU activation function; the other technique entails relaxing the homotopy parameter to enhance the training refinement process. We have conducted an in-depth analysis of this novel method within the context of the neural tangent kernel (NTK), revealing significantly improved convergence rates. Our experimental results, especially when considering networks with larger widths, validate the theoretical conclusions. This proposed HRTA exhibits the potential for other activation functions and deep neural networks.

📄 PDF Abstract BibTeX arXiv:2309.15244

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Homotopy relations for digital images

2015-09-22 · Laurence Boxer, P. Christopher Staecker

We introduce three generalizations of homotopy equivalence in digital images, to allow us to express whether a finite and an infinite digital image are similar with respect to homotopy. We show that these three general…

Homotopy based algorithms for $\ell_0$-regularized least-squares

2014-01-31 · Charles Soussen, Jérôme Idier, Junbo Duan, David Brie

Sparse signal restoration is usually formulated as the minimization of a quadratic cost function $\|y-Ax\|_2^2$, where A is a dictionary and x is an unknown sparse vector. It is well-known that imposing an $\ell_0$ const…

Heuristic Search

Convex Formulations for Training Two-Layer ReLU Neural Networks

2024-10-29 · Karthik Prakhya, Tolga Birdal, Alp Yurtsever

Solving non-convex, NP-hard optimization problems is crucial for training machine learning models, including neural networks. However, non-convexity often leads to black-box machine learning models with unclear inner wor…

Continuation Path Learning for Homotopy Optimization

2023-07-24 · Xi Lin, Zhiyuan Yang, Xiaoyuan Zhang, Qingfu Zhang

Homotopy optimization is a traditional method to deal with a complicated optimization problem by solving a sequence of easy-to-hard surrogate subproblems. However, this method can be very sensitive to the continuation sc…

Decision Making

A conditional gradient homotopy method with applications to Semidefinite Programming

2022-07-07 · Pavel Dvurechensky, Gabriele Iommazzo, Shimrit Shtern, Mathias Staudigl

We propose a new homotopy-based conditional gradient method for solving convex optimization problems with a large number of simple conic constraints. Instances of this template naturally appear in semidefinite programmin…

Combinatorial Optimization