Search Results for author:
Found 4 papers, 1 papers with code
Massively scalable Sinkhorn distances via the Nyström method
The Sinkhorn "distance", a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference.
Online learning over a finite action set with limited switching
Using the above result and several reductions, we unify previous work and completely characterize the complexity of this switching budget setting up to small polylogarithmic factors: for both PFE and MAB, for all switching budgets $S \leq T$, and for both expectation and h. p.
Best Arm Identification for Contaminated Bandits
Specifically, we propose a variant of the Best Arm Identification problem for \emph{contaminated bandits}, where each arm pull has probability $\varepsilon$ of generating a sample from an arbitrary contamination distribution instead of the true underlying distribution.
Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
Computing optimal transport distances such as the earth mover's distance is a fundamental problem in machine learning, statistics, and computer vision.
