HTTP/2 301
date: Wed, 31 Dec 2025 11:15:39 GMT
content-type: text/html; charset=utf-8
location: https://slideslive.com/38985646/improved-analysis-for-the-proximal-sampler
cache-control: no-cache
content-security-policy: frame-ancestors 'none'
nel: {"report_to":"heroku-nel","response_headers":["Via"],"max_age":3600,"success_fraction":0.01,"failure_fraction":0.1}
referrer-policy: strict-origin-when-cross-origin
report-to: {"group":"heroku-nel","endpoints":[{"url":"https://nel.heroku.com/reports?s=tJIxtciJ9NN1CM9TJ0rO44Q4c67FNwM6zOlkUGDwus4%3D\u0026sid=e11707d5-02a7-43ef-b45e-2cf4d2036f7d\u0026ts=1767179739"}],"max_age":3600}
reporting-endpoints: heroku-nel="https://nel.heroku.com/reports?s=tJIxtciJ9NN1CM9TJ0rO44Q4c67FNwM6zOlkUGDwus4%3D&sid=e11707d5-02a7-43ef-b45e-2cf4d2036f7d&ts=1767179739"
server: cloudflare
set-cookie: _sl_session_v2=vJQHLSIyvsQuJbp2zmBrEEiwGcmv2Dk%2BzjA%2Fed8Ni7gfpVmltYoift%2Fqll3P8PYcddSkxu%2BC2iiwsse3EKuZp1jlLScXGo0W6g7D1TzG1NAOhmFjiUwlqZ3x2pJZNmiO%2FpYrQ5KfIx%2BuvJmTVCYdq549uCxtokZGzsm0LP0J2b7vhDTZ2iknUoGXDgw7u0XEOS7L1n5HEzhMhi63DANpsdjULEUVFow2CUxLGf7pCtwWo4hE9wTQ1ugNFzN%2FkMWwJRcn78o69MnARHanBiv742kMltoUwoHBaKzbs7baMeLnPcA8bbdN50b7w8efg8pOAkDTRFZKUhzv4jqhasHf9w%3D%3D--euNBerpv0CsbopA1--4%2F4Md8q6DZ%2Ftrv2xpxhjeQ%3D%3D; domain=slideslive.com; path=/; expires=Mon, 31 Dec 2035 11:15:39 GMT; secure; httponly; SameSite=None; Partitioned;
strict-transport-security: max-age=0; includeSubDomains
vary: Content-Type, Accept-Encoding, Origin
via: 2.0 heroku-router
x-content-type-options: nosniff
x-download-options: noopen
x-frame-options: DENY
x-permitted-cross-domain-policies: none
x-request-id: 61fbf565-7d7a-0b7a-e351-b6628fc97bd8
x-runtime: 0.017046
x-xss-protection: 0
cf-cache-status: DYNAMIC
cf-ray: 9b695c3a8d6bf473-BLR
alt-svc: h3=":443"; ma=86400
HTTP/2 200
date: Wed, 31 Dec 2025 11:15:40 GMT
content-type: text/html; charset=utf-8
cache-control: max-age=0, private, must-revalidate
content-security-policy: frame-ancestors 'none'
nel: {"report_to":"heroku-nel","response_headers":["Via"],"max_age":3600,"success_fraction":0.01,"failure_fraction":0.1}
referrer-policy: strict-origin-when-cross-origin
report-to: {"group":"heroku-nel","endpoints":[{"url":"https://nel.heroku.com/reports?s=AlQ7cGnXw0uGMPM%2FLcN03qgYlxOK5ky7M3bPhBV71wQ%3D\u0026sid=e11707d5-02a7-43ef-b45e-2cf4d2036f7d\u0026ts=1767179740"}],"max_age":3600}
reporting-endpoints: heroku-nel="https://nel.heroku.com/reports?s=AlQ7cGnXw0uGMPM%2FLcN03qgYlxOK5ky7M3bPhBV71wQ%3D&sid=e11707d5-02a7-43ef-b45e-2cf4d2036f7d&ts=1767179740"
server: cloudflare
set-cookie: _sl_session_v2=emBKfJ3K%2BbOMP7UPn%2BoxrfW9edsvK4h%2FJhyAZOVq0LPGDACaL7LSYbPd8os4VeS31QRxmwMin3itamjA5bpk%2F%2BC2l%2BCbB%2FYzhi70IuCX5J2NhqOjYWFMxSVfo31m%2FpGQUYDR6LJlbo8JRp4uXSeruRGYnj4UZWvZjHT5GMzY1azRhdvthe9nJFsyrZ64sZI3f%2FELmCrT%2FmId962LrUyJKPeSavTpQyv%2BHD4XeZFvhxlwDtxF9qJBgjEAn63QCrGapZ3FLa2cGzoH5hcQPXYmQKibgKZ8cxtN%2FAYkh9H8jJ7UiIlEEcygANcS1ZydP00fpnmSiThxLf7HtiAsxdTUAFHKBVl%2BcyVlO2R0zy4j7FuFJz13c%2BzkNKPJphkBCxuugQl4EWX7xW0TzDj7TGcTbEWdtVFhwAKozzbd553VbV6o7T7pu2gwGIUQjMFXC6v6--BhigjO6JSmy7KWde--862TE2s77AJ2udU2WAGteg%3D%3D; domain=slideslive.com; path=/; expires=Mon, 31 Dec 2035 11:15:40 GMT; secure; httponly; SameSite=None; Partitioned;
strict-transport-security: max-age=0; includeSubDomains
vary: Content-Type, Accept-Encoding, Origin
via: 2.0 heroku-router
x-content-type-options: nosniff
x-download-options: noopen
x-frame-options: DENY
x-permitted-cross-domain-policies: none
x-request-id: 3973e967-6ccd-f95c-805a-71cfdc7192ad
x-runtime: 0.100955
x-xss-protection: 0
cf-cache-status: DYNAMIC
content-encoding: gzip
cf-ray: 9b695c3eea7bf473-BLR
alt-svc: h3=":443"; ma=86400
Sinho Chewi, Yongxin Chen, Adil Salim, Andre Wibisono · Improved analysis for the proximal sampler · SlidesLive
COLT
COLT 2022
Improved analysis for the proximal sampler
Improved analysis for the proximal sampler
Jul 2, 2022
About
We study the proximal sampler of Lee, Shen, and Tian (2021) and obtain new convergence guarantees under weaker assumptions than strong log-concavity: namely, our results hold for (1) weakly log-concave targets, and (2) targets satisfying isoperimetric assumptions which allow for non-log-concavity. We demonstrate our results by obtaining new state-of-the-art sampling guarantees for several classes of target distributions. We also strengthen the connection between the proximal sampler and the proximal method in optimization by interpreting the former as an entropically regularized Wasserstein gradient flow and the latter as the limit of one.
Show more
Show less
About COLT
The conference is held annually since 1988 and has become the leading conference on Learning theory by maintaining a highly selective process for submissions. It is committed in high-quality articles in all theoretical aspects of machine learning and related topics.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Show advanced options
Recommended Videos
Presentations on similar topic, category or speaker
Interested in talks like this? Follow COLT
