Theory / Machine Learning Talk December 6, 2019 3:30pm — 4:30pm Location: ASA Conference Room 6115 (new location) - Gates Hillman Centers Speaker: LORENZO ORECCHIA, Assistant Professor https://www.cs.uchicago.edu/people/profile/lorenzo-orecchia/ We present a novel approach to analyze and design first-order methods for convex optimization via the calculus of variations. Specifically, we show that the continuous-time dynamics underlying these methods arise as the unique solutions of the minimization of natural convex functionals over the space of absolutely continuous paths from a given starting point. While previous work has characterized these continuous-time dynamics as critical points of certain functionals, i.e., solutions to Euler-Lagrange equations, our work is the first to give a convex formulation of these functionals. An interesting upshot of this work is that the problem of designing continuous-time first-order methods for convex optimization is itself a convex optimization problem. Faculty Host: Gary L. Miller Appointments For More Information: rmcardle@andrew.cmu.edu Add event to Google Add event to iCal
