Nick Harvey (Univ. of British Columbia, Vancouver)
Monday, October 26, 2020
Virtual via Bluejeans - 11:00 am
Title: Optimal anytime regret with two experts
Abstract: A central problem in online learning is regret minimization in the expert setting. The famous multiplicative weights method achieves the optimal regret asymptotically if the number of experts is large, and the time horizon is known in advance. Optimal algorithms are also known if there are exactly two, three or four experts, and the time horizon is known in advance.
In the “anytime” setting, where the time horizon is not known in advance, algorithms can be obtained by the “doubling trick”, but they are not optimal, let alone practical. No minimax optimal algorithm was previously known in the anytime setting, regardless of the number of experts. We design the first minimax optimal algorithm for minimizing regret in the anytime setting. We consider the case of two experts, and prove that the optimal regret is \gamma \sqrt{t}/2 at all time steps t, where \gamma is a natural constant that arose 35 years ago in studying fundamental properties of Brownian motion. The algorithm is designed by considering a continuous analogue of the regret problem, which is solved using ideas from stochastic calculus.
----------------------------------
Videos of recent talks are available at: http://arc.gatech.edu/node/121
Click here to subscribe to the seminar email list: arc-colloq@Klauscc.gatech.edu
]]>