Academics

Recent theoretical advances in non convex optimization

Time:2022-12-15 Thu 14:00-16:00

Venue:Venue: 1129B Zoom: 537 192 5549(PW: BIMSA)

Organizer:Wuyue Yang, Fansheng Xiong, Xiaopei Jiao

Speaker: Xiaopei Jiao

Abstract

In this report, we give an overview of recent theoretical results on global performance guarantees of optimization algorithm for non convex optimization about deep neural network and data analysis.

DATEDecember 15, 2022
SHARE
Related News
    • 0

      AdaBB: A Parameter-Free Gradient Method for Convex Optimization

      Organizer:Chenglong Bao 包承龙Speaker:Shiqian Ma (Rice University)Time:Thur., 11:00 am -12:00, Nov. 14, 2024Online:Tencent Meeting:127-784-846Title:AdaBB: A Parameter-Free Gradient Method for Convex OptimizationAbstract:We propose AdaBB, an adaptive gradient method based on the Barzilai-Borwein stepsize. The algorithm is line-search-free and parameter-free, and essentially provides a conv...

    • 1

      Convex real projective structures on reflection orbifolds

      Organizers陈伟彦、高鸿灏、黄意、林剑锋、孙巍峰SpeakerGye-Seon LEESeoul National UniversityTimeMonday, 10:00 - 11:00 amApril 21, 2025VenueC654, Shuangqing Complex BuildingZoom meeting ID: 405 416 0815pw: 111111Convex real projective structures on reflection orbifolds Let O be a compact reflection n-orbifold whose underlying space is homeomorphic to a truncation n-polytope, i.e. a polytope obtain...