Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Large-Scale Wasserstein Gradient Flows
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-013-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-013-alpha.b-cdn.net
      • sl-yoda-v3-stream-013-beta.b-cdn.net
      • 1668715672.rsc.cdn77.org
      • 1420896597.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
            Large-Scale Wasserstein Gradient Flows
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Large-Scale Wasserstein Gradient Flows

            Dez 6, 2021

            Sprecher:innen

            PM

            Petr Mokrov

            Sprecher:in · 0 Follower:innen

            AK

            Alexander Korotin

            Sprecher:in · 0 Follower:innen

            LL

            Lingxiao Li

            Sprecher:in · 0 Follower:innen

            Über

            Wasserstein gradient flows provide a powerful means of understanding and solving many diffusion equations. Specifically, Fokker-Planck equations, which model the diffusion of probability measures, can be understood as gradient descent over entropy functionals in Wasserstein space. This equivalence, introduced by Jordan, Kinderlehrer and Otto, inspired the so-called JKO scheme to approximate these diffusion processes via an implicit discretization of the gradient flow in Wasserstein space. Solvin…

            Organisator

            N2
            N2

            NeurIPS 2021

            Konto · 1,9k Follower:innen

            Über NeurIPS 2021

            Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.

            Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!

            Professionelle Aufzeichnung und Livestreaming – weltweit.

            Freigeben

            Empfohlene Videos

            Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind

            Out-of-Distribution Generalization in Kernel Regression
            15:07

            Out-of-Distribution Generalization in Kernel Regression

            Abdul Canatar, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Conditioning Variational Gaussian Processes for Online Decision-making
            11:30

            Conditioning Variational Gaussian Processes for Online Decision-making

            Wesley Maddox, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Beyond Fairness in Machine Learning
            4:39:12

            Beyond Fairness in Machine Learning

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Live panel: The future of ImageNet
            1:06:30

            Live panel: The future of ImageNet

            Lucas Beyer, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Learning to Execute (L2E): Efficient Learning of Plan-Conditioned Policies in Robotics
            08:36

            Learning to Execute (L2E): Efficient Learning of Plan-Conditioned Policies in Robotics

            Ingmar Schubert, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Interessiert an Vorträgen wie diesem? NeurIPS 2021 folgen