Katya Scheinberg

 

Katya Scheinberg is a Coca-Cola Foundation Chair and Professor at the H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology. Prior to joining Georgia Tech she held positions at Cornell and Lehigh Universities and at IBM T.J. Watson Research Center. She attended Moscow University for her undergraduate studies and received her PhD degree from Columbia University. Katya’s main research areas are related to developing practical algorithms (and their theoretical analysis) for various problems in continuous optimization, such as convex optimization, derivative free optimization, machine learning, quadratic programming, etc. She is an Informs Fellow, a recipient of the Lagrange Prize from SIAM and MOS, the Farkas Prize from Informs Optimization Society and the Outstanding Simulation Publication award from Informs Simulation Society. Katya is currently the editor-in-chief of Mathematics of Operations Research, and co-editor of Mathematical Programming. She is a Chair-Elect of the Mathematical Optimization Society.

Title of talk: Stochastic oracles and where to find them

Majority of modern optimization 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.