Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Indexed Minimal Empirical Divergence for Unimodal Bandits
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-016-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-016-alpha.b-cdn.net
      • sl-yoda-v3-stream-016-beta.b-cdn.net
      • 1504562137.rsc.cdn77.org
      • 1896834465.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
            Indexed Minimal Empirical Divergence for Unimodal Bandits
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Indexed Minimal Empirical Divergence for Unimodal Bandits

            Dec 6, 2021

            Speakers

            HS

            Hassan Saber

            Speaker · 0 followers

            PM

            Pierre Ménard

            Speaker · 0 followers

            OM

            Odalric-Ambrym Maillard

            Speaker · 0 followers

            About

            We consider a stochastic multi-armed bandit problem specified by a set of one-dimensional family exponential distributions endowed with a unimodal structure. The unimodal structure is of practical relevance for several applications. We introduce IMED-UB, an algorithm that exploits provably optimally the unimodal-structure, by adapting to this setting the Indexed Minimum Empirical Divergence (IMED) algorithm introduced by Honda and Takemura (2015). Owing to our proof technique, we are able to pro…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 1.9k followers

            About 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.

            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

            Random Noise Defense Against Query-Based Black-Box Attacks
            12:53

            Random Noise Defense Against Query-Based Black-Box Attacks

            Zeyu Qin, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Dynamic Trace Estimation
            14:13

            Dynamic Trace Estimation

            Prathamesh Dharangutte, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Towards Building a Responsible Data Economy
            50:31

            Towards Building a Responsible Data Economy

            Dawn Song

            N2
            N2
            NeurIPS 2021 3 years ago

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

            A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
            11:15

            A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis

            Xingang Pan, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Data preparation for training CNNs: Application to vibration-based condition monitoring
            02:08

            Data preparation for training CNNs: Application to vibration-based condition monitoring

            Vahid Yaghoubi, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Federated Multi-Task Learning under a Mixture of Distributions
            13:13

            Federated Multi-Task Learning under a Mixture of Distributions

            Othmane Marfoq, …

            N2
            N2
            NeurIPS 2021 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 NeurIPS 2021