Neural Information Processing Systems http://nips.cc/

In the most basic setting of this problem, an agent has to pull one among a finite set of arms (or actions), and she receives a reward that depends on the chosen action.

We propose a new exact minibatch MH method, TunaMH, which exposes a tunable trade-off between its batch size and its theoretically guaranteed convergence rate.

Given a convex function f: Rd R, the problem of sampling from a distribution e f(x) is called log-concave sampling. This task has wide applications in machine learning, physics, statistics, etc.

This fast mixing guarantee can hold in cases when global mixing is provably slow.