2026-09-19T09:29:54Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1513332023-08-01T04:09:39Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022
Rigollet, Philippe
Chewi, Sinho
Massachusetts Institute of Technology. Department of Mathematics
2023-07-31T19:32:02Z
2023-07-31T19:32:02Z
2023-06
2023-05-24T14:46:43.264Z
https://hdl.handle.net/1721.1/151333
0000-0003-2701-0703
The primary contribution of this thesis is to advance the theory of complexity for sampling from a continuous probability density over R^d. Some highlights include: a new analysis of the proximal sampler, taking inspiration from the proximal point algorithm in optimization; an improved and sharp analysis of the Metropolis-adjusted Langevin algorithm, yielding new state-of-the-art guarantees for high-accuracy log-concave sampling; the first lower bounds for the complexity of log-concave sampling; an analysis of mirror Langevin Monte Carlo for constrained sampling; and the development of a theory of approximate first-order stationarity in non-log-concave sampling.
We further illustrate the main tools in this work—diffusions and Wasserstein gradient flows—through applications to functional inequalities, the entropic barrier, Wasserstein barycenters, variational inference, and diffusion models.
Ph.D.
Massachusetts Institute of Technology
Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Copyright retained by author(s)
https://creativecommons.org/licenses/by-sa/4.0/
An optimization perspective on log-concave sampling and beyond
Thesis
application/pdf
Doctoral
Doctor of Philosophy
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="30cf421a-9d8c-4ee1-aeed-7eae3ca45a74">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>An optimization perspective on log-concave sampling and beyond</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2023-06</PublicationDate>
<Authors>
<Author>
<DisplayName>Chewi, Sinho</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://creativecommons.org/licenses/by-sa/4.0/</License>
<Abstract>The primary contribution of this thesis is to advance the theory of complexity for sampling from a continuous probability density over R^d. Some highlights include: a new analysis of the proximal sampler, taking inspiration from the proximal point algorithm in optimization; an improved and sharp analysis of the Metropolis-adjusted Langevin algorithm, yielding new state-of-the-art guarantees for high-accuracy log-concave sampling; the first lower bounds for the complexity of log-concave sampling; an analysis of mirror Langevin Monte Carlo for constrained sampling; and the development of a theory of approximate first-order stationarity in non-log-concave sampling.
We further illustrate the main tools in this work—diffusions and Wasserstein gradient flows—through applications to functional inequalities, the entropic barrier, Wasserstein barycenters, variational inference, and diffusion models.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>