Efficient Alternatives to Min-Max Models

A Google TechTalk, presented by Nisheeth Vishnoi, 2020/10/30 Paper Title: "Convergent and Practical Algorithms for Nonconvex-Nonconcave Min-Max Optimization" ABSTRACT: While there has been incredible progress in convex and nonconvex minimization, many problems in machine learning are in need of efficient algorithms to solve min-max optimization problems. However, unlike minimization, where algorithms can always be shown to converge to some local minimum, there is no notion of local equilibrium in min-max optimization that exists for general nonconvex-nonconcave functions. We will present new notions of local equilibria that are guaranteed to exist, efficient algorithms to compute them, and implications to GANs. About the Speaker: Nisheeth Vishnoi is a Professor of Computer Science and a co-founder of the Computation and Society Initiative at Yale University. His research focuses on foundational problems in computer science, machine learning, and optimization. He is also broadly interested in understanding and addressing some of the key questions that arise in nature and society from a computational viewpoint. Here, his current focus is on natural algorithms, the emergence of intelligence, and algorithmic fairness. He was the recipient of the Best Paper Award at IEEE FOCS in 2005, the IBM Research Pat Goldberg Memorial Award in 2006, the Indian National Science Academy Young Scientist Award in 2011, the IIT Bombay Young Alumni Achievers Award in 2016, and the Best Technical Paper award at ACM FAT* in 2019. He was elected an ACM Fellow in 2019. He holds a B. Tech., Computer Science and Engineering, Indian Institute of Technology Bombay, 1995-1999, Ph. D., Algorithms, Combinatorics and Optimization, Georgia Institute of Technology, 1999-2004.