Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-011-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-011-alpha.b-cdn.net
      • sl-yoda-v3-stream-011-beta.b-cdn.net
      • 1150868944.rsc.cdn77.org
      • 1511650057.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
            Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs

            Dez 6, 2021

            Sprecher:innen

            HZ

            Han Zhong

            Sprecher:in · 0 Follower:innen

            JH

            Jiayi Huang

            Sprecher:in · 0 Follower:innen

            LFY

            Lin F. Yang

            Sprecher:in · 0 Follower:innen

            Über

            Despite a large amount of effort in dealing with heavy-tailed error in machine learning, little is known when moments of the error can become non-existential: the random noise η satisfies Pr[|η| > |y|] < 1/|y|^α for some α > 0. We make the first attempt to actively handle such super heavy-tailed noise in bandit learning problems: We propose a novel robust statistical estimator, mean of medians, which estimates a random variable by computing the empirical mean of a sequence of empirical…

            Organisator

            N2
            N2

            NeurIPS 2021

            Konto · 1,9k Follower:innen

            Über NeurIPS 2021

            Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.

            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

            Identifiability in Inverse Reinforcement Learning
            15:07

            Identifiability in Inverse Reinforcement Learning

            Haoyang Cao, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Unleashing the Power of Industrial Big Data through Scalable Manual Labeling
            02:08

            Unleashing the Power of Industrial Big Data through Scalable Manual Labeling

            Bruno Paes Leao, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Hierarchical Reinforcement Learning with Timed Subgoals
            08:17

            Hierarchical Reinforcement Learning with Timed Subgoals

            Nico Gürtler, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Shortcuts and Example Selection in Contrastive Learning
            30:20

            Shortcuts and Example Selection in Contrastive Learning

            Stefanie Jegelka, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity
            15:06

            Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity

            Vladimir Ivanov, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Machine Learning through Database Glasses
            40:30

            Machine Learning through Database Glasses

            Dan Olteanu

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Interessiert an Vorträgen wie diesem? NeurIPS 2021 folgen