June 21, 2024, 4:48 a.m. | H\'edi Hadiji (UvA), Sarah Sachs (UvA), Crist\'obal Guzm\'an (UC)

cs.LG updates on arXiv.org arxiv.org

arXiv:2406.14059v1 Announce Type: cross
Abstract: Tracking the solution of time-varying variational inequalities is an important problem with applications in game theory, optimization, and machine learning. Existing work considers time-varying games or time-varying optimization problems. For strongly convex optimization problems or strongly monotone games, these results provide tracking guarantees under the assumption that the variation of the time-varying problem is restrained, that is, problems with a sublinear solution path. In this work we extend existing results in two ways: In our …

abstract applications arxiv cs.gt cs.lg game games game theory important machine machine learning math.oc optimization problem results solution solutions stat.ml theory tracking type variation work

AI Focused Biochemistry Postdoctoral Fellow

@ Lawrence Berkeley National Lab | Berkeley, CA

Senior Data Engineer

@ Displate | Warsaw

Hybrid Cloud Engineer

@ Vanguard | Wayne, PA

Senior Software Engineer

@ F5 | San Jose

Software Engineer, Backend, 3+ Years of Experience

@ Snap Inc. | Bellevue - 110 110th Ave NE

Global Head of Commercial Data Foundations

@ Sanofi | Cambridge