Search Machine Learning Repository:
Adaptive Monte Carlo via Bandit Allocation
Authors: James Neufeld, Andras Gyorgy, Csaba Szepesvari and Dale Schuurmans
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Abstract: We consider the problem of sequentially choosing between a set of unbiased Monte Carlo estimators to minimize the mean-squared-error (MSE) of a final combined estimate. By reducing this task to a stochastic multi-armed bandit problem, we show that well developed allocation strategies can be used to achieve an MSE that approaches that of the best estimator chosen in retrospect. We then extend these developments to a scenario where alternative estimators have different, possibly stochastic, costs. The outcome is a new set of adaptive Monte Carlo strategies that provide stronger guarantees than previous approaches while offering practical advantages.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).