Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Last-Iterate Convergence in No-regret Learning: Constrained Min-Max Optimization for Convex-Concave Landscapes
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-015-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-015-alpha.b-cdn.net
      • sl-yoda-v3-stream-015-beta.b-cdn.net
      • 1963568160.rsc.cdn77.org
      • 1940033649.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
            Last-Iterate Convergence in No-regret Learning: Constrained Min-Max Optimization for Convex-Concave Landscapes
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Last-Iterate Convergence in No-regret Learning: Constrained Min-Max Optimization for Convex-Concave Landscapes

            Apr 14, 2021

            Speakers

            IP

            Ioannis Panageas

            Speaker · 0 followers

            QL

            Qi Lei

            Speaker · 0 followers

            SGN

            Sai Ganesh Nagarajan

            Speaker · 0 followers

            About

            In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games. Specifically, Daskalakis et al 2018, Liang-Stokes 2019, show last iterate convergence of the so called ``Optimistic Gradient Descent/Ascent" for the case of \textit{unconstrained} min-max optimization. Moreover, in Mertikopoulos et al 2019 the authors show that Mirror Descent with an extra gradient step displays last i…

            Organizer

            A2
            A2

            AISTATS 2021

            Account · 63 followers

            Categories

            Natural & Formal Sciences

            Category · 3.3k presentations

            About AISTATS 2021

            The 24th International Conference on Artificial Intelligence and Statistics was held virtually from Tuesday, 13 April 2021 to Thursday, 15 April 2021.

            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

            Oral: Quick Streaming Algorithms for Maximization of Monotone Submodular Functions in Linear Time
            12:53

            Oral: Quick Streaming Algorithms for Maximization of Monotone Submodular Functions in Linear Time

            Alan Kuhnle

            A2
            A2
            AISTATS 2021 4 years ago

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

            Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
            03:01

            Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization

            Vikas K. Garg, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Training a Single Bandit Arm
            03:26

            Training a Single Bandit Arm

            Eren Ozbay, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Provably Safe PAC-MDP Exploration Using Analogies
            02:51

            Provably Safe PAC-MDP Exploration Using Analogies

            Melrose Roderick, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Robust Learning under Strong Noise via SQs
            03:04

            Robust Learning under Strong Noise via SQs

            Ioannis Anagnostides, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Transforming  Gaussian Processes With Normalizing Flows
            03:05

            Transforming Gaussian Processes With Normalizing Flows

            Juan Maroñas, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Interested in talks like this? Follow AISTATS 2021