AI Seminar Series 2022: Binghshan Hu

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On Jan 21, Binghshan Hu – an Amii Postdoctoral Fellow– presented "(Near)-optimal Regret Bound for Differentially Private Thompson Sampling" at the AI Seminar.

A multi-armed bandit problem is a classical sequential decision-making problem in which the goal is to accumulate as much reward as possible. In this learning model, only a limited amount of information is revealed in each round. The imperfect feedback model results in the learning algorithm being in a dilemma between exploration (gaining information) and exploitation (accumulating reward). Thompson Sampling is one of the classical learning algorithms that can make a good balance between exploration and exploitation and it always has a very competitive empirical performance. In the standard non-private learning, the learning algorithm can always get access to the true revealed information to make future decisions. However, if the revealed information is about individuals, to preserve privacy, the decisions made by the learning algorithm should not rely on the true revealed information. In this talk, Hu presents a Thompson Sampling-based algorithm, DP-TS, for private stochastic bandits. The regret upper bound for DP-TS matches the discovered regret lower bound up to an extra loglogT factor.

Watch the full presentation below:

Keep up-to-date on the AI Seminar Series by signing up for the mailing list.

Learn how Amii advances world-leading artificial intelligence and machine learning research: visit our Research page.