BARC talk by Mikael Møller Høgsgaard

Thursday, November 14, 2024, Mikael Møller Høgsgaard, PhD student at Aarhus University, Denmark, will give a talk on "Majority-of-Three: The Simplest Optimal Learner?".

Abstract:
Developing an optimal PAC learning algorithm in the realizable setting, where empirical risk minimization (ERM) is suboptimal, was a major open problem in learning theory for decades. The problem was finally resolved by Hanneke a few years ago. Unfortunately, Hanneke's algorithm is quite complex as it returns the majority vote of many ERM classifiers that are trained on carefully selected subsets of the data. It is thus a natural goal to determine the simplest algorithm that is optimal. In this work we study the arguably simplest algorithm that could be optimal: returning the majority vote of three ERM classifiers. We show that this algorithm achieves the optimal in-expectation bound on its error which is provably unattainable by a single ERM classifier. Furthermore, we prove a near-optimal high-probability bound on this algorithm's error. We conjecture that a better analysis will prove that this algorithm is in fact optimal in the high-probability regime.

Bio:
Mikael is a third year PhD student at Aarhus University supervised by Professor Kasper Green Larsen. His primary interest is learning theory. To see his list of publications, follow this link: ‪Mikael Møller Høgsgaard‬ - ‪Google Scholar‬

Host:
Amik Raj Behera and Amir Yehudayoff