Speaker : 류경석 교수님 (Prof. Ernest K. Ryu, Seoul National University)
Date : 16:00-17:00, Nov. 19, 2020
Place : AORC Seminar Room, General Studies Bd. 3F
Title : Minimax Optimization in Machine Learning
Abstract:
In this talk, we will talk about generative adversarial networks and convergence guarantees in stochastic *minimax* optimization under the assumption of convex-concavity. Specifically, we establish almost sure convergence and L2 convergence in the last-iterates and present optimal accelerated complexity of minimizing gradients in the noiseless setting.