About

I am a final-year PhD student in the EECS department 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.

My research is at the interface of optimization, probability, and machine learning. I am particularly interested in optimization problems over probability distributions, with a recent focus on problems related to optimal transport.

I am interested in practical implementations as well as theory. In summer 2021, I interned under Kunal Talwar in Apple’s new research team on differential privacy. I've previously interned at Google Research, Tower Research, and DE Shaw. While I was an undergrad at Princeton, I was fortunate to work with Elad Hazan and Emmanuel Abbe.

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

--> I am co-organizing a workshop on Optimal Transport and Machine Learning at NeurIPS 2021. Please submit your exciting new work!

Publications

Preprints under review

• Kernel approximation on algebraic varieties
  Jason Altschuler, Pablo Parrilo.
  Preprint, 2021.
  

• Asymptotics for semi-discrete entropic optimal transport
  Jason Altschuler, Jonathan Niles-Weed, Austin Stromme.
  Preprint, 2021.
  

• Polynomial-time algorithms for Multimarginal Optimal Transport problems with structure
  Jason Altschuler, Enric Boix-Adsera.
  Preprint, 2020.
  

• Approximating Min-Mean-Cycle for low-diameter graphs in near-optimal time and memory
  Jason Altschuler, Pablo Parrilo.
  Preprint, 2020.
  

• Near-linear convergence of the Random Osborne algorithm for Matrix Balancing
  Jason Altschuler, Pablo Parrilo.
  Preprint, 2020.
  

Journal articles

• Wasserstein barycenters are NP-hard to compute
  Jason Altschuler, Enric Boix-Adsera.
  SIAM Journal on Mathematics of Data Science (SIMODS), 2021, to appear.
  

• Wasserstein barycenters can be computed in polynomial time in fixed dimension [poster, talk, slides]
  Jason Altschuler, Enric Boix-Adsera.
  Journal of Machine Learning Research (JMLR), 2021.
  

• Hardness results for Multimarginal Optimal Transport problems
  Jason Altschuler, Enric Boix-Adsera.
  Discrete Optimization (DISOPT), 2021.
  

• Lyapunov Exponent of Rank One Matrices: Ergodic Formula and Inapproximability of the Optimal Distribution [slides]
  Jason Altschuler, Pablo Parrilo.
  SIAM Journal on Control and Optimization (SICON), 2020. (Preliminary conference version in CDC)

• Online learning over a finite action set with limited switching [poster, talk]
  Jason Altschuler, Kunal Talwar.
  Mathematics of Operations Research (MOR), 2021. (Preliminary conference version in COLT)

• Best arm identification for contaminated bandits
  Jason Altschuler, Victor-Emmanuel Brunel, Alan Malek.
  Journal of Machine Learning Research (JMLR), 2019.

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

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

Conference proceedings

• Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent
  Jason Altschuler, Sinho Chewi, Patrik Gerber, Austin Stromme.
  Neural Information Processing Systems (NeurIPS), 2021, to appear. (Selected for Spotlight presentation)
  

• Lyapunov Exponent of Rank One Matrices: Ergodic Formula and Inapproximability of the Optimal Distribution [slides]
  Jason Altschuler, Pablo Parrilo.
  Conference on Decision and Control (CDC), 2019.

• Massively scalable Sinkhorn distances via the Nyström method
  Jason Altschuler, Francis Bach, Alessandro Rudi, Jonathan Niles-Weed.
  Neural Information Processing Systems (NeurIPS), 2019.
  

• Online learning over a finite action set with limited switching [poster, talk]
  Jason Altschuler, Kunal Talwar.
  Conference on Learning Theory (COLT), 2018.

• Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration [poster]
  Jason Altschuler, Jonathan Weed, Philippe Rigollet.
  Neural Information Processing Systems (NeurIPS), 2017. (Selected for Spotlight presentation)
  

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

Teaching

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