papers

Publications (7)

stat.ML2019

Massively scalable Sinkhorn distances via the Nyström method

Jason Altschuler, Francis Bach, Alessandro Rudi +1

The Sinkhorn "distance", a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference. However,…

cs.DS2018

Approximating the Quadratic Transportation Metric in Near-Linear Time

Jason Altschuler, Francis Bach, Alessandro Rudi +1

Computing the quadratic transportation metric (also called the -Wasserstein distance or root mean square distance) between two point clouds, or, more generally, two discrete dis…

cs.DS2016

Greedy Column Subset Selection: New Bounds and Distributed Algorithms

Jason Altschuler, Aditya Bhaskara, Gang Fu +3

The problem of column subset selection has recently attracted a large body of research, with feature selection serving as one obvious and important application. Among the technique…

cs.DS2018

Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration

Jason Altschuler, Jonathan Weed, Philippe Rigollet

Computing optimal transport distances such as the earth mover's distance is a fundamental problem in machine learning, statistics, and computer vision. Despite the recent introduct…

math.ST2019

Best Arm Identification for Contaminated Bandits

Jason Altschuler, Victor-Emmanuel Brunel, Alan Malek

This paper studies active learning in the context of robust statistics. Specifically, we propose a variant of the Best Arm Identification problem for \emph{contaminated bandits}, w…

math.CO2017

Inclusion of Forbidden Minors in Random Representable Matroids

Jason Altschuler, Elizabeth Yang

In 1984, Kelly and Oxley introduced the model of a random representable matroid corresponding to a random matrix , whose entries are…