Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Universal Online Learning with Bounded Loss: Reduction to Binary Classification
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-007-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-007-alpha.b-cdn.net
      • sl-yoda-v2-stream-007-beta.b-cdn.net
      • 1678031076.rsc.cdn77.org
      • 1932936657.rsc.cdn77.org
      • Subtitles
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Universal Online Learning with Bounded Loss: Reduction to Binary Classification
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Universal Online Learning with Bounded Loss: Reduction to Binary Classification

            Jul 2, 2022

            Speakers

            MB

            Moise Blanchard

            Speaker · 0 followers

            RC

            Romain Cosson

            Speaker · 0 followers

            About

            We study universal consistency of non-i.i.d. processes in the context of online learning. A stochastic process is said to admit universal consistency if there exists a learner that achieves vanishing average loss for any measurable response function on this process. When the loss function is unbounded, [1] showed that the only processes admitting strong universal consistency are those taking a finite number of values almost surely. However, when the loss function is bounded, the class of process…

            Organizer

            C
            C

            COLT

            Account · 1 follower

            About COLT

            The conference is held annually since 1988 and has become the leading conference on Learning theory by maintaining a highly selective process for submissions. It is committed in high-quality articles in all theoretical aspects of machine learning and related topics.

            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

            Thompson Sampling Achieves  𝒪̃(√T) Regret in Linear Quadratic Control
            12:43

            Thompson Sampling Achieves 𝒪̃(√T) Regret in Linear Quadratic Control

            Taylan Kargin, …

            C
            C
            COLT 3 years ago

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

            Reducibility and Statistical-Computational Gaps from Secret Leakage
            15:09

            Reducibility and Statistical-Computational Gaps from Secret Leakage

            Matthew S Brennan, …

            C
            C
            COLT 5 years ago

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

            Tsallis-INF for Decoupled Exploration and Exploitation in Multi-armed Bandits
            15:29

            Tsallis-INF for Decoupled Exploration and Exploitation in Multi-armed Bandits

            Chloé Rouyer, …

            C
            C
            COLT 5 years ago

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

            A Corrective View of Neural Networks: Representation,  Memorization and Learning
            01:03

            A Corrective View of Neural Networks: Representation, Memorization and Learning

            Dheeraj M Nagaraj, …

            C
            C
            COLT 5 years ago

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

            Tracking Most Significant Arm Switches in Bandits
            13:45

            Tracking Most Significant Arm Switches in Bandits

            Joe Suk, …

            C
            C
            COLT 3 years ago

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

            Differential privacy and robust statistics in high dimensions
            16:00

            Differential privacy and robust statistics in high dimensions

            Xiyang Liu, …

            C
            C
            COLT 3 years ago

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

            Interested in talks like this? Follow COLT