Web: http://arxiv.org/abs/2108.06808

Jan. 28, 2022, 2:11 a.m. | Yan Li, Caleb Ju, Ethan X. Fang, Tuo Zhao

cs.LG updates on arXiv.org arxiv.org

Bregman proximal point algorithm (BPPA), as one of the centerpieces in the
optimization toolbox, has been witnessing emerging applications. With simple
and easy to implement update rule, the algorithm bears several compelling
intuitions for empirical successes, yet rigorous justifications are still
largely unexplored. We study the computational properties of BPPA through
classification tasks with separable data, and demonstrate provable algorithmic
regularization effects associated with BPPA. We show that BPPA attains
non-trivial margin, which closely depends on the condition number of …

algorithm arxiv data

More from arxiv.org / cs.LG updates on arXiv.org

Director, Data Engineering and Architecture

@ Chainalysis | California | New York | Washington DC | Remote - USA

Deep Learning Researcher

@ Topaz Labs | Dallas, TX

Sr Data Engineer (Contractor)

@ SADA | US - West

Senior Cloud Database Administrator

@ Findhelp | Remote

Senior Data Analyst

@ System1 | Remote

Speech Machine Learning Research Engineer

@ Samsung Research America | Mountain View, CA