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


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
Related News
    • 0

      Advances in Homotopy Theory IV

      This is the fourth edition of a twice-yearly workshop that will alternate between the Southampton Centre for Geometry, Topology and Applications and the Beijing Institute of Mathematical Sciences and Applications. The aims are to promote exciting new work in homotopy theory, with an emphasis on that by younger mathematicians, and to showcase the wide relevance of the subject to other areas of m...

    • 1

      Recent advance on Nesterov acceleration

      AbstractNesterov's accelerated gradient descent (NAG) is one of the milestones in the history of first-order algorithms. Until recently, it was not successfully uncovered by the high-resolution differential equation framework in [Shi et al., 2021] that the mechanism behind the acceleration phenomenon is due to the gradient correction term. Along this way, I present some recent advances about th...