all AI news
Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients
April 24, 2024, 4:42 a.m. | Sachin Garg, Albert S. Berahas, Micha{\l} Derezi\'nski
cs.LG updates on arXiv.org arxiv.org
Abstract: We show that, for finite-sum minimization problems, incorporating partial second-order information of the objective function can dramatically improve the robustness to mini-batch size of variance-reduced stochastic gradient methods, making them more scalable while retaining their benefits over traditional Newton-type approaches. We demonstrate this phenomenon on a prototypical stochastic second-order algorithm, called Mini-Batch Stochastic Variance-Reduced Newton ($\texttt{Mb-SVRN}$), which combines variance-reduced gradient estimates with access to an approximate Hessian oracle. In particular, we show that when the …
abstract arxiv benefits cs.lg function gradient information making math.oc robustness scalable show stat.ml stochastic sum them type variance
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Data Engineer - Takealot Group (Takealot.com | Superbalist.com | Mr D Food)
@ takealot.com | Cape Town