About

I am a second year PhD student at MIT. I am fortunate to be advised by Pablo Parrilo. My current research interests are at the intersection of convex optimization and (randomized) approximation algorithms. I am supported by an NSF GRFP grant.

Previously, I completed my undergrad at Princeton University (class of '16) under the wonderful supervision of Elad Hazan and Emmanuel Abbe. I spent 2 of my undergrad summers interning in tech (at Google/Google Research) and the other 2 summers interning on Wall Street (DE Shaw and Tower Research Capital).

In my free time, I like to play chess. I obtained an International Master norm in Spain in 2015.

Publications

Recent papers

• Online learning over a finite action set with limited switching
  Jason Altschuler, Kunal Talwar.
  Preprint, 2018.

• Best arm identification for contaminated bandits
  Jason Altschuler, Victor-Emmanuel Brunel, Alan Malek.
  Preprint, 2018.

• Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
  Jason Altschuler, Jonathan Weed, Philippe Rigollet.
  Neural Information Processing Systems (NIPS), 2017. (Selected for Spotlight presentation)
  3-minute overview NIPS video, poster, code on Github

• Inclusion of forbidden minors in random representable matroids
  Jason Altschuler, Elizabeth Yang.
  Discrete Mathematics, 2017.

• Greedy column subset selection: new bounds and distributed algorithms
  Jason Altschuler, Aditya Bhaskara, Gang Fu, Vahab Mirrokni, Afshin Rostamizadeh, Morteza Zadimoghaddam.
  International Conference for Machine Learning (ICML), 2016.
  Video of my ICML talk, talk slides, poster

High school

• Rapid analysis and exploration of fluorescence microscopy images
  Benjamin Pavie, Satwik Rajaram, Austin Ouyang, Jason Altschuler, Robert Steininger, Lani Wu, Steven Altschuler.
  Journal of Visual Experiments (JoVE), 2014.

Theses and other unpublished stuff

• Approximation algorithms for Independent Set via semidefinite programming hierarchies and randomized rounding
  Jason Altschuler, Matt Brennan.
  Expository final project for David Karger's Randomized Algorithms course (MIT 6.856), 2017.
  

• Minimax rates for online learning with limited decision changes (superseded by this paper.)
  Undergrad thesis for Princeton CS department, advised by Elad Hazan, 2016.
  

• Probabilistic variants of Rota's so-called "critical problem" in combinatorics and coding theory
  Undergrad thesis for Princeton math department, advised by Emmanuel Abbe, 2016.
  

Teaching

• COS 511: Theoretical machine learning (graduate) -- Spring 2016
• MAT 340: Applied algebra -- Fall 2015
• MAT 216: Accelerated honors real analysis -- Fall 2014
• MAT 217: Honors linear algebra -- Spring 2014
• MAT 215: Honors real analysis -- Fall 2013