Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-001-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-001-alpha.b-cdn.net
      • sl-yoda-v2-stream-001-beta.b-cdn.net
      • 1824830694.rsc.cdn77.org
      • 1979322955.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
            Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations

            Nov 28, 2022

            Sprecher:innen

            JZH

            Jeff Z. HaoChen

            Sprecher:in · 0 Follower:innen

            CW

            Colin Wei

            Sprecher:in · 2 Follower:innen

            AK

            Ananya Kumar

            Sprecher:in · 1 Follower:in

            Über

            Contrastive learning is a highly effective method for learning representations from unlabeled data. Recent works show that contrastive representations can transfer across domains, leading to simple state-of-the-art algorithms for unsupervised domain adaptation. In particular, a linear classifier trained to separate the representations on the source domain can also predict classes on the target domain accurately, even though the representations of the two domains are far from each other. We refer…

            Organisator

            N2
            N2

            NeurIPS 2022

            Konto · 956 Follower:innen

            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

            What You See is What You Classify: Black Box Attributions
            04:33

            What You See is What You Classify: Black Box Attributions

            Steven Stalder, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Differentiable Analog Quantum Computing for Optimization and Control
            04:46

            Differentiable Analog Quantum Computing for Optimization and Control

            Jiaqi Leng, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization
            09:49

            Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization

            Elan Rosenfeld, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Laplacian Autoencoders for Stochastic Representations Learning
            05:03

            Laplacian Autoencoders for Stochastic Representations Learning

            Marco Miani, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            GLIPv2: Unifying Localization and Vision-Language Understanding
            05:34

            GLIPv2: Unifying Localization and Vision-Language Understanding

            Haotian Zhang, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems
            05:03

            Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems

            Pouria Mahdavinia, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Interessiert an Vorträgen wie diesem? NeurIPS 2022 folgen