Statistics Colloquium: Ashwin Pananjady
11:30 am–12:30 pm Jones 303
Ashwin Pananjady, H. Milton Stewart School of Industrial and Systems Engineering/The School of Electrical and Computer Engineering, Georgia Institute of Technology
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.
