Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Demped Sinkhorn Iterations
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-008-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-008-alpha.b-cdn.net
      • sl-yoda-v2-stream-008-beta.b-cdn.net
      • 1159783934.rsc.cdn77.org
      • 1511376917.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
            Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Demped Sinkhorn Iterations
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Demped Sinkhorn Iterations

            Dec 10, 2023

            Speakers

            TV

            Tomas Vaskevicius

            Řečník · 0 sledujících

            LC

            Lénaïc Chizat

            Řečník · 1 sledující

            About

            We study the computation of doubly regularized Wasserstein barycenters, a recently introduced family of entropic barycenters governed by inner and outer regularization strengths. Previous research has demonstrated that various regularization parameter choices unify several notions of entropy-penalized barycenters while also revealing new ones, including a special case of debiased barycenters. In this paper, we propose and analyze an algorithm for computing doubly regularized Wasserstein barycent…

            Organizer

            N2
            N2

            NeurIPS 2023

            Účet · 646 sledujících

            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

            Training Fully Connected Neural Networks is ∃ℝ-Complete
            04:18

            Training Fully Connected Neural Networks is ∃ℝ-Complete

            Daniel Bertschinger, …

            N2
            N2
            NeurIPS 2023 16 months ago

            Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %

            Learning Runtime Decisions for Adaptive Real-Time Perception
            04:12

            Learning Runtime Decisions for Adaptive Real-Time Perception

            Anurag Ghosh, …

            N2
            N2
            NeurIPS 2023 16 months ago

            Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %

            OOPS..There is a Distribution Mismatch in the SVHN Dataset
            03:59

            OOPS..There is a Distribution Mismatch in the SVHN Dataset

            Tim Z. Xiao, …

            N2
            N2
            NeurIPS 2023 16 months ago

            Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %

            Direct Preference Optimization: Your Language Model is Secretly a Reward Model
            05:25

            Direct Preference Optimization: Your Language Model is Secretly a Reward Model

            Rafael Rafailov, …

            N2
            N2
            NeurIPS 2023 16 months ago

            Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %

            What does scale give us: Why we are building a ladder to the moon
            32:10

            What does scale give us: Why we are building a ladder to the moon

            Sara Hooker

            N2
            N2
            NeurIPS 2023 16 months ago

            Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %

            QuIP: 2-Bit Quantization of LLMs With Theoretical Guarantees
            04:57

            QuIP: 2-Bit Quantization of LLMs With Theoretical Guarantees

            Jerry Chee, …

            N2
            N2
            NeurIPS 2023 16 months ago

            Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %

            Interested in talks like this? Follow NeurIPS 2023