Saved in:
Bibliographic Details
Main Authors: Yan, Chengcheng, Xu, Jiawei, Peng, Zheng, Wang, Qingsong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.04193
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918115829350400
author Yan, Chengcheng
Xu, Jiawei
Peng, Zheng
Wang, Qingsong
author_facet Yan, Chengcheng
Xu, Jiawei
Peng, Zheng
Wang, Qingsong
contents The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and high computational cost. To address these issues, we propose a novel method, Stochastic Alternating Minimization with Trainable Step Sizes (SAMT), which updates network parameters in an alternating manner by treating the weights of each layer as a block. By decomposing the overall optimization into sub-problems corresponding to different blocks, this block-wise alternating strategy reduces per-step computational overhead and enhances training stability in nonconvex settings. To fully leverage these benefits, inspired by meta-learning, we proposed a novel adaptive step size strategy to incorporate into the sub-problem solving steps of alternating updates. It supports different types of trainable step sizes, including but not limited to scalar, element-wise, row-wise, and column-wise, enabling adaptive step size selection tailored to each block via meta-learning. We further provide a theoretical convergence guarantee for the proposed algorithm, establishing its optimization soundness. Extensive experiments for multiple benchmarks demonstrate that SAMT achieves better generalization performance with fewer parameter updates compared to state-of-the-art methods, highlighting its effectiveness and potential in neural network optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04193
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
Yan, Chengcheng
Xu, Jiawei
Peng, Zheng
Wang, Qingsong
Machine Learning
The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and high computational cost. To address these issues, we propose a novel method, Stochastic Alternating Minimization with Trainable Step Sizes (SAMT), which updates network parameters in an alternating manner by treating the weights of each layer as a block. By decomposing the overall optimization into sub-problems corresponding to different blocks, this block-wise alternating strategy reduces per-step computational overhead and enhances training stability in nonconvex settings. To fully leverage these benefits, inspired by meta-learning, we proposed a novel adaptive step size strategy to incorporate into the sub-problem solving steps of alternating updates. It supports different types of trainable step sizes, including but not limited to scalar, element-wise, row-wise, and column-wise, enabling adaptive step size selection tailored to each block via meta-learning. We further provide a theoretical convergence guarantee for the proposed algorithm, establishing its optimization soundness. Extensive experiments for multiple benchmarks demonstrate that SAMT achieves better generalization performance with fewer parameter updates compared to state-of-the-art methods, highlighting its effectiveness and potential in neural network optimization.
title Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
topic Machine Learning
url https://arxiv.org/abs/2508.04193