Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with an Inexact Prox
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-002-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-002-alpha.b-cdn.net
      • sl-yoda-v2-stream-002-beta.b-cdn.net
      • 1001562353.rsc.cdn77.org
      • 1075090661.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with an Inexact Prox
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with an Inexact Prox

            Dec 6, 2022

            Speakers

            AS

            Abdurakhmon Sadiev

            Speaker · 0 followers

            DK

            Dmitry Kovalev

            Speaker · 0 followers

            PR

            Peter Richtárik

            Speaker · 0 followers

            About

            Inspired by a recent breakthrough of Mishchenko et al. [2022], who for the first time showed that local gradient steps can lead to provable communication acceleration, we propose an alternative algorithm which obtains the same communication acceleration as their method (ProxSkip). Our approach is very different, however: it is based on the celebrated method of Chambolle and Pock [2011], with several nontrivial modifications: i) we allow for an inexact computation of the prox operator of a certai…

            Organizer

            N2
            N2

            NeurIPS 2022

            Account · 954 followers

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Understanding A Class of Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective
            04:05

            Understanding A Class of Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective

            Xinwei Zhang, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Multi-Modal Conditional GAN: Data Synthesis in the Medical Domain
            02:00

            Multi-Modal Conditional GAN: Data Synthesis in the Medical Domain

            Jonathan D. Ziegler

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Deterministically Constrained Stochastic Optimization
            42:17

            Deterministically Constrained Stochastic Optimization

            Frank E. Curtis, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            A gradient sampling method with complexity guarantees for Lipschitz functions in low and high dimensions
            02:27

            A gradient sampling method with complexity guarantees for Lipschitz functions in low and high dimensions

            Damek Davis, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Towards Modeling Complete Potentials in Crystal Materials
            45:35

            Towards Modeling Complete Potentials in Crystal Materials

            Shuiwang Ji

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
            05:04

            CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

            Karel D'Oosterlinck, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow NeurIPS 2022