Katya Scheinberg: Stochastic First Order Oracles and Where to Find Them

Submitted by Tony I Garcia on

The Department of Applied Mathematics is pleased to host this series of colloquium lectures, funded in part by a generous gift from the Boeing Company. This series will bring to campus prominent applied mathematicians from around the world.

Speaker: Katya Scheinberg

Date: October 21st, 2021

Location: (SMI 205)

Title: Stochastic First Order Oracles and Where to Find Them

Abstract: Continuous optimization is a mature field, which has recently undergone major expansion and change. One of the key new directions is the development of methods that do not require exact information about the objective function. Nevertheless majority of these methods, from stochastic gradient descent to "zero-th order" methods use some kind of approximate first order information. We will overview different methods of obtaining this information, including simple stochastic gradient via sampling, robust gradient estimation in adversarial settings, traditional and randomized finite difference methods and more.

We will discuss what key properties of these inexact, stochastic first order oracles are useful for convergence analysis of optimization methods that use them.

Youtube: Watch the talk online here