One of the fundamental issues facing deployment of supervised learning models in real life applications is the issue of out-of-distribution (OOD) generalization.

Artificial Intelligence, specifically machine learning (ML), has increasingly been making inroads into society and our lives over the last decade.

Given n-variate polynomials f,g,h such that f=g/h, where both g and h are computable by arithmetic circuits of size s, we show that f can be computed by a circuit of size poly(s, deg(h)).

In this talk, I will introduce the problem of determining the identity of a byzantine user (internal adversary) in a communication system.