You are here

Seminar on Theoretical Machine Learning

Online Control with Adversarial Disturbances

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that has full knowledge of the disturbances in hindsight. Our main result is an efficient algorithm that provides nearly tight regret bounds for this problem. From a technical standpoint, this work generalizes upon previous work in that our model allows for adversarial noise in the dynamics and allows for general convex costs.

Featuring

Naman Agarwal

Speaker Affiliation

Online Control with Adversarial Disturbances

Affiliation

Mathematics

Event Series

Date & Time
February 11, 2019 | 12:151:45pm

Location

White Levy Room

Categories