IEOR-DRO Seminar: Katya Scheinberg (Lehigh)

September 5, 2017 | 1:10pm - 2:00pm

IEOR-DRO Seminar: Katya Scheinberg (Lehigh)

Mudd Hall, 500 W. 120 St., New York, NY 10027 303
Abstract: We will present a very general framework for unconstrained stochastic optimization which is based on standard  frameworks such as line search and trust region using  random models. In particular this framework retains the desirable features such step acceptance criterion, trust region adjustment and ability to utilize of second order models. We make assumptions on the stochasticity that are different from the typical assumptions of stochastic and simulation-based optimization. In particular we assume that our models and function values satisfy some good quality conditions with some fixed probability, but can be arbitrarily bad otherwise. We will analyze the convergence and convergence rates of this general framework and discuss the requirement on the models and function values. 

We will motivate the framework with examples of applications arising the area of machine learning. We will contrast our results with existing results from stochastic approximation and machine learning literature. 

Bio: Katya Scheinberg is the Harvey E. Wagner Endowed Chair Professor at the Industrial and Systems Engineering Department at Lehigh University. 

She attended Moscow University for her undergraduate studies in applied mathematics and then moved to New York and received her PhD degree in operations research from Columbia University.  After receiving her doctoral degree she has  worked  at the IBM T.J. Watson Research Center as a research staff member for over a decade before joining Lehigh in 2010. In 2016-2017 Katya spent her sabbatical leave visiting Google Research in NY and University of Oxford. 
 
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 has been focusing on large-scale optimization method for Big Data applications and Machine Learning since 2000.  In 2015, jointly with Andy Conn and Luis Vicente, she received  the Lagrange Prize awarded jointly by SIAM and MOS. Katya is the editor-in-chief of SIAM-MOS Optimization book series and an associate editor of Mathematical Programming and SIAM Journal on Optimization. 



500 W. 120th St., Mudd 315, New York, NY 10027    212-854-2942                 
©2014 Columbia University