Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-012-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-012-alpha.b-cdn.net
      • sl-yoda-v3-stream-012-beta.b-cdn.net
      • 1338956956.rsc.cdn77.org
      • 1656830687.rsc.cdn77.org
      • Subtitles
      • Off
      • en
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems

            Jul 12, 2020

            Sprecher:innen

            FH

            Filip Hanzely

            Sprecher:in · 0 Follower:innen

            DK

            Dmitry Kovalev

            Sprecher:in · 0 Follower:innen

            PR

            Peter Richtarik

            Sprecher:in · 0 Follower:innen

            Über

            We propose an accelerated version of stochastic variance reduced coordinate descent – ASVRCD. As other variance reduced coordinate descent methods such as SEGA or SVRCD, our method can deal with problems that include a non-separable and non-smooth regularizer, while accessing a random block of partial derivatives in each iteration only. However, ASVRCD incorporates Nesterov's momentum, which offers favorable iteration complexity guarantees over both SEGA and SVRCD. As a by-product of our theory,…

            Organisator

            I2
            I2

            ICML 2020

            Konto · 2,6k Follower:innen

            Kategorien

            Mathematik

            Kategorie · 2,4k Präsentationen

            Über ICML 2020

            The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

            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

            T-GD: Transferable GAN-generated Images Detection Framework
            14:18

            T-GD: Transferable GAN-generated Images Detection Framework

            Hyeonseong Jeon, …

            I2
            I2
            ICML 2020 5 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Leveraging Frequency Analysis for Deep Fake Image Recognition
            12:44

            Leveraging Frequency Analysis for Deep Fake Image Recognition

            Joel Frank, …

            I2
            I2
            ICML 2020 5 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            WiML Diversity and Inclusion Chairs
            08:14

            WiML Diversity and Inclusion Chairs

            Sinead Williamson, …

            I2
            I2
            ICML 2020 5 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Rigging the Lottery: Making All Tickets Winners (RigL)
            12:59

            Rigging the Lottery: Making All Tickets Winners (RigL)

            Utku Evci, …

            I2
            I2
            ICML 2020 5 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle
            13:32

            Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle

            Shaocong Ma, …

            I2
            I2
            ICML 2020 5 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Submodular Optimization: From Discrete to Continuous and Back - Part IV
            44:13

            Submodular Optimization: From Discrete to Continuous and Back - Part IV

            Hamed Hassani, …

            I2
            I2
            ICML 2020 5 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Interessiert an Vorträgen wie diesem? ICML 2020 folgen