Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Fast Projection onto the Capped Simplex with Applications to Sparse Regression in Bioinformatics
      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
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Fast Projection onto the Capped Simplex with Applications to Sparse Regression in Bioinformatics
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Fast Projection onto the Capped Simplex with Applications to Sparse Regression in Bioinformatics

            Dec 6, 2021

            Speakers

            AA

            Andersen Ang

            Speaker · 0 followers

            JM

            JianZhu Ma

            Speaker · 0 followers

            NL

            Nianjun Liu

            Speaker · 0 followers

            About

            We consider the problem of projecting a vector onto the so-called k-capped simplex, which is a hyper-cube cut by a hyperplane.For an n-dimensional input vector with bounded elements, we found that a simple algorithm based on Newton's method is able to solve the projection problem to high precision with a complexity roughly about O(n), which has a much lower computational cost compared with the existing sorting-based methods proposed in the literature.We provide a theory for partial explanation a…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 128 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

            Tensor Normal Training for Deep Learning Models
            04:14

            Tensor Normal Training for Deep Learning Models

            Yi Ren, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Learning a Subspace of Policies for Online Adaptation in Reinforcement Learning
            05:04

            Learning a Subspace of Policies for Online Adaptation in Reinforcement Learning

            Jean-Baptiste Gaya, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Improved Regularization and Robustness for Fine-tuning in Neural Networks
            12:03

            Improved Regularization and Robustness for Fine-tuning in Neural Networks

            Dongyue Li, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
            05:41

            Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance

            Shibal Ibrahim, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Modeling and Inference in Biology: A Modest Overview of DGMs Applications in Computational Biology
            21:56

            Modeling and Inference in Biology: A Modest Overview of DGMs Applications in Computational Biology

            Romain Lopez

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Nearly Horizon-Free Offline Reinforcement Learning
            08:44

            Nearly Horizon-Free Offline Reinforcement Learning

            Tongzheng Ren, …

            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