Sinho Chewi

Sinho Chewi

Massachusetts Institute of Technology

H-index: 16

North America-United States

About Sinho Chewi

Sinho Chewi, With an exceptional h-index of 16 and a recent h-index of 16 (since 2020), a distinguished researcher at Massachusetts Institute of Technology, specializes in the field of optimal transport, probability, sampling, statistics.

His recent articles reflect a diverse array of research interests and contributions to the field:

The probability flow ODE is provably fast

Sampling from the mean-field stationary distribution

Fast parallel sampling under isoperimetry

Fisher information lower bounds for sampling

On the complexity of finding stationary points of smooth functions in one dimension

Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions

An entropic generalization of Caffarelli’s contraction theorem via covariance inequalities

Shifted composition II: shift Harnack inequalities and curvature upper bounds

Sinho Chewi Information

University

Position

PhD Student

Citations(all)

779

Citations(since 2020)

777

Cited By

30

hIndex(all)

16

hIndex(since 2020)

16

i10Index(all)

22

i10Index(since 2020)

22

Email

University Profile Page

Google Scholar

Sinho Chewi Skills & Research Interests

optimal transport

probability

sampling

statistics

Top articles of Sinho Chewi

The probability flow ODE is provably fast

Advances in Neural Information Processing Systems

2024/2/13

Sampling from the mean-field stationary distribution

arXiv preprint arXiv:2402.07355

2024/2/12

Sinho Chewi
Sinho Chewi

H-Index: 3

Fast parallel sampling under isoperimetry

arXiv preprint arXiv:2401.09016

2024/1/17

Nima Anari
Nima Anari

H-Index: 15

Sinho Chewi
Sinho Chewi

H-Index: 3

Fisher information lower bounds for sampling

2023/2/13

On the complexity of finding stationary points of smooth functions in one dimension

2023/2/13

Sinho Chewi
Sinho Chewi

H-Index: 3

Adil Salim
Adil Salim

H-Index: 6

Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions

arXiv preprint arXiv:2209.11215

2022/9/22

An entropic generalization of Caffarelli’s contraction theorem via covariance inequalities

Comptes Rendus. Mathématique

2023

Sinho Chewi
Sinho Chewi

H-Index: 3

Shifted composition II: shift Harnack inequalities and curvature upper bounds

arXiv preprint arXiv:2401.00071

2023/12/29

Sinho Chewi
Sinho Chewi

H-Index: 3

Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space

arXiv preprint arXiv:2312.02849

2023/12/5

Sinho Chewi
Sinho Chewi

H-Index: 3

Shifted composition I: Harnack and reverse transport inequalities

arXiv preprint arXiv:2311.14520

2023/11/24

Sinho Chewi
Sinho Chewi

H-Index: 3

Query lower bounds for log-concave sampling

2023/11/6

Faster high-accuracy log-concave sampling via algorithmic warm starts

2023/11/6

Sinho Chewi
Sinho Chewi

H-Index: 3

The entropic barrier is n-self-concordant

2023/9/30

Sinho Chewi
Sinho Chewi

H-Index: 3

Improved discretization analysis for underdamped Langevin Monte Carlo

2023/7/12

Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Space

2023/7/3

An optimization perspective on log-concave sampling and beyond

2023/5/1

Sinho Chewi
Sinho Chewi

H-Index: 3

Gaussian discrepancy: a probabilistic relaxation of vector balancing

Discrete Applied Mathematics

2022/12/15

Sinho Chewi
Sinho Chewi

H-Index: 3

Philippe Rigollet
Philippe Rigollet

H-Index: 27

Learning threshold neurons via the "edge of stability"

arxiv.org/2212.07469

2022/12/14

Variational inference via Wasserstein gradient flows

Advances in Neural Information Processing Systems

2022/12/6

Improved analysis for a proximal algorithm for sampling

2022/6/28

See List of Professors in Sinho Chewi University(Massachusetts Institute of Technology)

Co-Authors

academic-engine