vix.ing · top · new · best · stats

Variance Regularization for Accelerating Stochastic Optimization

2020/08/13 by Tong Yang, Yang, Tong, Long Sha +3
Computer Science · Decision Sciences · Engineering · Mathematics · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques #cs.LG #math.OC #stat.ML

paper · pdf · doi:10.48550/arxiv.2008.05969

22 pages, 3 figures

arxiv created 2020/08/13 · openalex publication_date 2020/08/13 · arxiv updated 2020/08/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

While nowadays most gradient-based optimization methods focus on exploring the high-dimensional geometric features, the random error accumulated in a stochastic version of any algorithm implementation has not been stressed yet. In this work, we propose a universal principle which reduces the random error accumulation by exploiting statistic information hidden in mini-batch gradients. This is achieved by regularizing the learning-rate according to mini-batch variances. Due to the complementarity of our perspective, this regularization could provide a further improvement for stochastic implementation of generic 1st order approaches. With empirical results, we demonstrated the variance regularization could speed up the convergence as well as stabilize the stochastic optimization.

Citations

Related