Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Representing Hyperbolic Space Accurately using Multi-Component Floats
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-015-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-015-alpha.b-cdn.net
      • sl-yoda-v3-stream-015-beta.b-cdn.net
      • 1963568160.rsc.cdn77.org
      • 1940033649.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
            Representing Hyperbolic Space Accurately using Multi-Component Floats
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Representing Hyperbolic Space Accurately using Multi-Component Floats

            Dec 6, 2021

            Speakers

            TY

            Tao Yu

            Speaker · 1 follower

            CDS

            Christopher De Sa

            Speaker · 1 follower

            About

            Hyperbolic space is very useful for embedding data with hierarchical structure; however, representing hyperbolic space with ordinary floating-point numbers greatly affects the performance due to its ineluctable numerical errors. Simply increasing the precision of floats fails to solve the problem and incurs a high computation cost for simulating greater-than-double-precision floats on hardware such as GPUs, which does not support them. In this paper, we propose a simple, feasible-on-GPUs, and ea…

            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

            Background and Scaffolding
            24:07

            Background and Scaffolding

            Vukosi Marivate, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Kernelized Heterogeneous Risk Minimization
            11:11

            Kernelized Heterogeneous Risk Minimization

            Jiashuo Liu, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
            05:55

            Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation

            Shiqi Yang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Stability and Generalization of Bilevel Programming in Hyperparameter Optimization
            08:58

            Stability and Generalization of Bilevel Programming in Hyperparameter Optimization

            Fan Bao, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            An Information Retrieval Approach to Building Datasets for Hate Speech Detection
            04:38

            An Information Retrieval Approach to Building Datasets for Hate Speech Detection

            Md Mustafizur Rahman, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Photometric Redshifts for Cosmology: Improving Accuracy and Uncertainty Estimates Using Bayesian Neural Networks
            04:41

            Photometric Redshifts for Cosmology: Improving Accuracy and Uncertainty Estimates Using Bayesian Neural Networks

            Evan Jones, …

            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