all AI news
Benign Underfitting of Stochastic Gradient Descent. (arXiv:2202.13361v3 [cs.LG] UPDATED)
June 8, 2022, 1:12 a.m. | Tomer Koren, Roi Livni, Yishay Mansour, Uri Sherman
stat.ML updates on arXiv.org arxiv.org
We study to what extent may stochastic gradient descent (SGD) be understood
as a "conventional" learning rule that achieves generalization performance by
obtaining a good fit to training data. We consider the fundamental stochastic
convex optimization framework, where (one pass, without-replacement) SGD is
classically known to minimize the population risk at rate $O(1/\sqrt n)$, and
prove that, surprisingly, there exist problem instances where the SGD solution
exhibits both empirical risk and generalization gap of $\Omega(1)$.
Consequently, it turns out that …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
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
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Software Engineer, Data Tools - Full Stack
@ DoorDash | Pune, India
Senior Data Analyst
@ Artsy | New York City