Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: SAM: Sharpness-aware Minimization for Efficiently Improving Generalization
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-008-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-008-alpha.b-cdn.net
      • sl-yoda-v2-stream-008-beta.b-cdn.net
      • 1159783934.rsc.cdn77.org
      • 1511376917.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
            SAM: Sharpness-aware Minimization for Efficiently Improving Generalization
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            SAM: Sharpness-aware Minimization for Efficiently Improving Generalization

            May 3, 2021

            Speakers

            PF

            Pierre Foret

            Speaker · 0 followers

            AK

            Ariel Kleiner

            Speaker · 0 followers

            HM

            Hossein Mobahi

            Speaker · 0 followers

            About

            In today's heavily overparameterized models, the value of the training loss provides few guarantees on model generalization ability. Indeed, optimizing only the training loss value, as is commonly done, can easily lead to suboptimal model quality. Motivated by prior work connecting the geometry of the loss landscape and generalization, we introduce a novel, effective procedure for instead simultaneously minimizing loss value and loss sharpness. In particular, our procedure, Sharpness-Aware Minim…

            Organizer

            I2
            I2

            ICLR 2021

            Account · 114 followers

            Categories

            AI & Data Science

            Category · 10.8k presentations

            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

            Closing remarks
            00:34

            Closing remarks

            Xavier Boix

            I2
            I2
            ICLR 2021 4 years ago

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

            Robust and Generalizable Visual Representation Learning via Random Convolutions
            05:06

            Robust and Generalizable Visual Representation Learning via Random Convolutions

            Zhenlin Xu, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Using system context information to complement weakly labeled data
            03:18

            Using system context information to complement weakly labeled data

            Matthias Meyer, …

            I2
            I2
            ICLR 2021 4 years ago

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

            Capturing Label Characteristics in VAEs
            05:35

            Capturing Label Characteristics in VAEs

            Tom Joy, …

            I2
            I2
            ICLR 2021 4 years ago

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

            A Temporal Kernel Approach for Deep Learning with Continuous-time Information
            04:20

            A Temporal Kernel Approach for Deep Learning with Continuous-time Information

            Da Xu, …

            I2
            I2
            ICLR 2021 4 years ago

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

            A Learning Theoretic Perspective on Local Explainability
            05:17

            A Learning Theoretic Perspective on Local Explainability

            Jeffrey Li, …

            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