Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Progressive Skeletonization: Trimming more fat from a network at initialization
      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
            Progressive Skeletonization: Trimming more fat from a network at initialization
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Progressive Skeletonization: Trimming more fat from a network at initialization

            May 3, 2021

            Speakers

            PdJ

            Pau de Jorge

            Speaker · 0 followers

            AS

            Amartya Sanyal

            Speaker · 0 followers

            HB

            Harkirat Behl

            Speaker · 0 followers

            About

            Recent studies have shown that skeletonization (pruning parameters) of networks at initialization provides all the practical benefits of sparsity both at inference and training time, while only marginally degrading their performance. However, we observe that beyond a certain level of sparsity (approx 95%), these approaches fail to preserve the network performance, and to our surprise, in many cases perform even worse than trivial random pruning. To this end, we propose an objective to find a ske…

            Organizer

            I2
            I2

            ICLR 2021

            Account · 887 followers

            About ICLR 2021

            The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.

            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

            Scientific NLP for COVID-19 and beyond
            29:24

            Scientific NLP for COVID-19 and beyond

            Lucy Lu Wang

            I2
            I2
            ICLR 2021 4 years ago

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

            Welcome from the Organisers
            07:54

            Welcome from the Organisers

            Colin Bellinger, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
            05:05

            Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques

            Filip Hanzely, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Natural Language Understanding with Incidental Supervision
            1:12:50

            Natural Language Understanding with Incidental Supervision

            Dan Roth

            I2
            I2
            ICLR 2021 4 years ago

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

            Training a First-Order Theorem Prover from Synthetic Data
            17:21

            Training a First-Order Theorem Prover from Synthetic Data

            Vlad Firoiu, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Unsupervised Discovery of 3D Physical Objects from Video
            05:15

            Unsupervised Discovery of 3D Physical Objects from Video

            Yilun Du, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Interested in talks like this? Follow ICLR 2021