Author
Timothee Mathieu
results may include different authors with the same name
2 papers
We study the non-contextual multi-armed bandit problem in a transfer learning setting: before any pulls, the learner is given N'_k i.i.d. samples from each source distribution nu'_k, and the true target distributions nu_k lie within a known…
Mean embeddings provide an extremely flexible and powerful tool in machine learning and statistics to represent probability distributions and define a semi-metric (MMD, maximum mean discrepancy; also called N-distance or energy distance),…