![]() |
Jason Altschuler
Email: jasonalt [at] mit [dot] edu |
I am a PhD student at MIT. I am fortunate to be advised by Pablo Parrilo. My research is supported by an NSF PhD fellowship and a TwoSigma PhD fellowship.
Previously, I was an undergrad at Princeton under the wonderful supervision of Elad Hazan and Emmanuel Abbe. I spent two of my undergrad summers interning in tech (at Google/Google Research) and the other two on Wall Street (DE Shaw and Tower Research).
In my free time, I like to play chess. I obtained an International Master norm in Spain in 2015.
Wasserstein barycenters are NP-hard to compute
[arxiv]
Jason Altschuler, Enric Boix-Adsera.
Preprint, 2021.
Hardness results for Multimarginal Optimal Transport problems
[arxiv]
Jason Altschuler, Enric Boix-Adsera.
Preprint, 2020.
Polynomial-time algorithms for Multimarginal Optimal Transport problems with decomposable structure
[arxiv]
Jason Altschuler, Enric Boix-Adsera.
Preprint, 2020.
Wasserstein barycenters can be computed in polynomial time in fixed dimension
[arxiv]
Jason Altschuler, Enric Boix-Adsera.
Journal of Machine Learning Research (JMLR), to appear, 2020+.
Approximating Min-Mean-Cycle for low-diameter graphs in near-optimal time and memory
[arxiv]
Jason Altschuler, Pablo Parrilo.
Preprint, 2020.
Random Osborne: a simple, practical algorithm for Matrix Balancing in near-linear time
[arxiv]
Jason Altschuler, Pablo Parrilo.
Preprint, 2020.
Lyapunov Exponent of Rank One Matrices: Ergodic Formula and Inapproximability of the Optimal Distribution
[arxiv, pub, slides]
Jason Altschuler, Pablo Parrilo.
Massively scalable Sinkhorn distances via the Nyström method
[arxiv, pub]
Jason Altschuler, Francis Bach, Alessandro Rudi, Jonathan Weed.
Conference on Neural Information Processing Systems (NeurIPS), 2019.
Best arm identification for contaminated bandits
[arxiv, pub]
Jason Altschuler, Victor-Emmanuel Brunel, Alan Malek.
Journal of Machine Learning Research (JMLR), 2019.
Online learning over a finite action set with limited switching
[arxiv, pub, poster, talk]
Jason Altschuler, Kunal Talwar.
Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
[arxiv, pub, poster]
Jason Altschuler, Jonathan Weed, Philippe Rigollet.
Conference on Neural Information Processing Systems (NeurIPS), 2017. (Selected for Spotlight presentation)
Inclusion of forbidden minors in random representable matroids
[arxiv, pub]
Jason Altschuler, Elizabeth Yang.
Discrete Mathematics, 2017.
Greedy column subset selection: new bounds and distributed algorithms
[arxiv, pub, poster, slides]
Jason Altschuler, Aditya Bhaskara, Gang Fu, Vahab Mirrokni, Afshin Rostamizadeh, Morteza Zadimoghaddam.
International Conference on Machine Learning (ICML), 2016.
Rapid analysis and exploration of fluorescence microscopy images
[pub]
Benjamin Pavie, Satwik Rajaram, Austin Ouyang, Jason Altschuler, Robert Steininger, Lani Wu, Steven Altschuler.
Journal of Visual Experiments (JoVE), 2014.
Approximation algorithms for Independent Set via semidefinite programming hierarchies and randomized rounding
[pdf]
Jason Altschuler, Matt Brennan.
Expository final project for David Karger's Randomized Algorithms course, 2017.
Minimax rates for online learning with limited decision changes (superseded by this paper in MOR/COLT)
Undergrad thesis for Princeton CS department, 2016. Advised by Elad Hazan.
Probabilistic linear Boolean classification
Undergrad thesis for Princeton math department, 2016. Advised by Emmanuel Abbe.