2026-09-19T07:43:28Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1392192022-01-15T03:49:54Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Sra, Suvrit
Ahn, Kwangjun
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-01-14T14:57:28Z
2022-01-14T14:57:28Z
2021-06
2021-06-24T19:07:14.990Z
https://hdl.handle.net/1721.1/139219
https://orcid.org/0000-0001-5516-5775
Recently, there has been significant effort to generalize successful ideas in Euclidean optimization to Riemannian optimization. However, one landmark result of Euclidean optimization has eluded the Riemannian setting: namely, a Riemannian analog of Nesterov's accelerated gradient method (AGM). In this thesis, we establish the first globally accelerated gradient method for Riemannian manifolds.
Toward establishing our result, the first part of the thesis revisits Nesterov's AGM and develops a conceptually simple understanding of it based on the proximal point method (PPM). The main observation is that AGM is in fact an approximation of PPM, which results in simple derivations and analyses of different versions of AGM.
The second part of the thesis then extends our simple approach to the Riemannian case. In our extension, we handle a technical hurdle inherent to the Riemannian case by introducing an appropriate notion of ``metric distortion.'' We control this distortion via a novel geometric inequality, which enables us to formulate and analyze global Riemannian acceleration.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
From Proximal Point Method to Accelerated Methods on Riemannian Manifolds
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="4a2bb3ef-0cff-494c-8a17-8bafb459250f">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>From Proximal Point Method to Accelerated Methods on Riemannian Manifolds</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2021-06</PublicationDate>
<Authors>
<Author>
<DisplayName>Ahn, Kwangjun</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Recently, there has been significant effort to generalize successful ideas in Euclidean optimization to Riemannian optimization. However, one landmark result of Euclidean optimization has eluded the Riemannian setting: namely, a Riemannian analog of Nesterov's accelerated gradient method (AGM). In this thesis, we establish the first globally accelerated gradient method for Riemannian manifolds.
Toward establishing our result, the first part of the thesis revisits Nesterov's AGM and develops a conceptually simple understanding of it based on the proximal point method (PPM). The main observation is that AGM is in fact an approximation of PPM, which results in simple derivations and analyses of different versions of AGM.
The second part of the thesis then extends our simple approach to the Riemannian case. In our extension, we handle a technical hurdle inherent to the Riemannian case by introducing an appropriate notion of ``metric distortion.'' We control this distortion via a novel geometric inequality, which enables us to formulate and analyze global Riemannian acceleration.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>