Narayanan, HariharanRakhlin, Alexander2023-05-232023-05-232010-01-012016-07-20https://repository.upenn.edu/handle/20.500.14332/47857We propose a computationally efficient random walk on a convex body which rapidly mixes to a time-varying Gibbs distribution. In the setting of online convex optimization and repeated games, the algorithm yields low regret and presents a novel efficient method for implementing mixture forecasting strategies.Statistics and ProbabilityRandom Walk Approach to Regret MinimizationPresentation