Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-009-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-009-alpha.b-cdn.net
      • sl-yoda-v2-stream-009-beta.b-cdn.net
      • 1766500541.rsc.cdn77.org
      • 1441886916.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
            Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption

            Jul 24, 2023

            Speakers

            VF

            Vasilii Feofanov

            Speaker · 0 followers

            MT

            Malik Tiomoko

            Speaker · 0 followers

            AV

            Aladin Virmaux

            Speaker · 0 followers

            About

            We propose a theoretical framework to analyze semi-supervised classification under the low density separation assumption in a high-dimensional regime. In particular, we introduce QLDS, a linear classification model, where the low density separation assumption is implemented via quadratic margin maximization. The algorithm has an explicit solution with rich theoretical properties, and we show that particular cases of our algorithm are the least-square support vector machine in the supervised case…

            Organizer

            I2
            I2

            ICML 2023

            Account · 629 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

            Artificial Intelligence and Computational Imaging: Opportunities for Precision Medicine
            37:22

            Artificial Intelligence and Computational Imaging: Opportunities for Precision Medicine

            Pallavi Tiwari

            I2
            I2
            ICML 2023 2 years ago

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

            MODel: Memory Optimizations for Deep Learning
            04:44

            MODel: Memory Optimizations for Deep Learning

            Benoit Steiner, …

            I2
            I2
            ICML 2023 2 years ago

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

            Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference
            07:01

            Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference

            Kyurae Kim, …

            I2
            I2
            ICML 2023 2 years ago

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

            Minimal Width for Universal Property of Deep RNN
            03:52

            Minimal Width for Universal Property of Deep RNN

            Chang Hoon Song, …

            I2
            I2
            ICML 2023 2 years ago

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

            On the Effectiveness of Offline RL for Dialogue Response Generation
            05:15

            On the Effectiveness of Offline RL for Dialogue Response Generation

            Paloma Sodhi, …

            I2
            I2
            ICML 2023 2 years ago

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

            Welcome and Opening Remarks
            09:43

            Welcome and Opening Remarks

            Katherine Lee, …

            I2
            I2
            ICML 2023 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 ICML 2023