Research

Publications

Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent. Jason Altschuler, Sinho Chewi, Patrik Gerber, and Austin Stromme. June 2021. [arXiv] [.bib]
The query complexity of sampling from strongly log-concave distributions in one dimension. Sinho Chewi, Patrik Gerber, Chen Lu, Thibaut Le Gouic, and Philippe Rigollet. June 2021. [arXiv] [.bib]
Rejection sampling from shape-constrained distributions in sublinear time. Sinho Chewi, Patrik Gerber, Chen Lu, Thibaut Le Gouic, and Philippe Rigollet. May 2021. [arXiv] [.bib]
Fast and smooth interpolation on Wasserstein space. Sinho Chewi, Julien Clancy, Thibaut Le Gouic, Philippe Rigollet, George Stepaniants, and Austin Stromme. March 2021. [arXiv] [AISTATS 2021] [.bib]
Dimension-free log-Sobolev inequalities for mixture distributions. Hong-Bin Chen, Sinho Chewi, and Jonathan Niles-Weed. February 2021. [arXiv] [Slides] [.bib]
Optimal dimension dependence of the Metropolis-adjusted Langevin algorithm. Sinho Chewi, Chen Lu, Kwangjun Ahn, Xiang Cheng, Thibaut Le Gouic, and Philippe Rigollet. December 2020. [arXiv] [.bib]
Exponential ergodicity of mirror-Langevin diffusions. Sinho Chewi, Thibaut Le Gouic, Chen Lu, Tyler Maunu, Philippe Rigollet, and Austin Stromme. December 2020. [arXiv] [NeurIPS 2020] [Slides] [.bib]
SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence. Sinho Chewi, Thibaut Le Gouic, Chen Lu, Tyler Maunu, and Philippe Rigollet. December 2020. [arXiv] [NeurIPS 2020] [Slides] [.bib]
Efficient constrained sampling via the mirror-Langevin algorithm. Kwangjun Ahn and Sinho Chewi. November 2020. [arXiv] [.bib]
Gradient descent algorithms for Bures-Wasserstein barycenters. Sinho Chewi, Tyler Maunu, Philippe Rigollet, and Austin Stromme. July 2020. [arXiv] [COLT 2020] [COLT 2020 (Video)] [Optimal Transport: Regularization and Applications 2020 (Video)] [TGDA@OSU 2020 (Video)] [Slides] [.bib]
Matching observations to distributions: efficient estimation via sparsified Hungarian algorithm. Sinho Chewi, Forest Yang, Avishek Ghosh, Abhay Parekh, and Kannan Ramchandran. September 2019. [arXiv] [Allerton 2019] [.bib]
A combinatorial proof of a formula of Biane and Chapuy. Sinho Chewi and Venkat Anantharam. March 2018. [arXiv] [E-JC] [.bib]

Teaching

Here is a list of courses that I have taught in the past.

Summer 2018

Computer Science 70 – Discrete Mathematics & Probability Theory [co-taught with Vrettos Moulos]

I have also been a TA for these courses.

Spring 2016

Computer Science 70 – Discrete Mathematics & Probability Theory (Satish Rao, Jean Walrand)

Fall 2016

Computer Science 70 – Discrete Mathematics & Probability Theory (Sanjit Seshia, Jean Walrand)

Spring 2017

Computer Science 70 – Discrete Mathematics & Probability Theory (Satish Rao)

Electrical Engineering 126 – Probability & Random Processes (Kannan Ramchandran)

Summer 2017

Computer Science 70 – Discrete Mathematics & Probability Theory (Hongling Lu, Vrettos Moulos, Allen Tang)

Fall 2017

Computer Science 70 – Discrete Mathematics & Probability Theory (Kannan Ramchandran, Satish Rao)

Electrical Engineering 126 – Probability & Random Processes (Abhay Parekh, Jean Walrand)

Spring 2018

Electrical Engineering 126 – Probability & Random Processes (Kannan Ramchandran)

I have led some Directed Reading Programs (DRP): 2019, 2020, 2021(A), 2021(B).

In 2016-2017, I won the EECS Outstanding GSI/Distinguished GSI Award.

Sinho Chewi's Website

Notes

18.137

Topics in Geometric PDEs

18.1521

Introduction to Partial Differential Equations

18.158

Topics in Differential Equations

18.176

Stochastic Calculus

18.338

Eigenvalues of Random Matrices

18.966

Geometry of Manifolds II

COMPSCI 229R

Topics in Theoretical Computer Science: Interactions between Physics and Computation

Other

Research

Publications

Teaching

Contact