Tilted Sampling
An online learning problem setting whose objective is to sample from the Gibbs soft-optimal distribution induced by an unknown reward function, rather than to identify a single optimal action. Its sampling regret is dominated by the squared confidence width, which permits regret guarantees on the order of log T.
Timeline (last 90 days)
Tilted sampling is a new online learning problem whose goal is to sample from the Gibbs distribution induced by an unknown reward function.
In standard regret minimization, the regret upper bound typically takes the form O(√T), whereas under the tilted sampling framework, sampling regret is dominated by the square of the confidence width, yielding logarithmic-level regret O(log T).
All Facts (2)
Tilted sampling is a new online learning problem whose goal is to sample from the Gibbs distribution induced by an unknown reward function.
50%UnverifiedIn standard regret minimization, the regret upper bound typically takes the form O(√T), whereas under the tilted sampling framework, sampling regret is dominated by the square of the confidence width, yielding logarithmic-level regret O(log T).
50%