AMS Weekly Seminar | Ashwin Pananjady

Location: Gilman 50

When: April 10th at 1:30 p.m.

Title: Predicting the behavior of complex iterative algorithms with random data

Abstract: Iterative algorithms are the workhorses of modern statistical signal processing and machine learning. Algorithm design and analysis is largely based on variational properties of the optimization problem, and the classical focus has been on obtaining convergence guarantees over classes of problems that possess certain types of geometry. However, modern optimization problems in statistical settings are high-dimensional and involve random data, and algorithms often behave differently from what is suggested by classical theory. With the motivation of better understanding optimization in such settings, I will present a toolbox for deriving “state evolutions” for a wide variety of algorithms with random data. These are non-asymptotic, near-exact predictions of the statistical behavior of the algorithm, which apply even when the underlying optimization problem is nonconvex or the algorithm is randomly initialized. We will showcase these predictions on deterministic and stochastic variants of complex algorithms employed in some canonical statistical models.

Bio: Ashwin Pananjady is the Gerald D. McInvale Early Career Professor and Assistant Professor at Georgia Tech, with a joint appointment between the H. Milton Stewart School of Industrial and Systems Engineering and the School of Electrical and Computer Engineering. His research in statistics, optimization and applied probability has been recognized by early-career awards from the Bernoulli Society and Institute of Mathematical Statistics, paper recognitions from the Mathematical Optimization Society, Applied Probability Society and Algorithmic Learning Theory conference, and research fellowships/awards from the Simons Institute, Amazon, and Adobe.

Zoom link: https://wse.zoom.us/j/93287142219?pwd=z9fqWnRMzmzS0SGijRiie5yN3kHRSZ.1