Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-002-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-002-alpha.b-cdn.net
      • sl-yoda-v2-stream-002-beta.b-cdn.net
      • 1001562353.rsc.cdn77.org
      • 1075090661.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
            Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

            Nov 28, 2022

            Speakers

            EN

            Eshaan Nichani

            Speaker · 0 followers

            YB

            Yu Bai

            Speaker · 0 followers

            JDL

            Jason D. Lee

            Speaker · 0 followers

            About

            A recent goal in the theory of deep learning is to identify how neural networks can escape the “lazy training,” or Neural Tangent Kernel (NTK) regime, where the network is coupled with its first order Taylor expansion at initialization. While the NTK is minimax optimal for learning dense polynomials (Ghorbani et al, 2021), it cannot learn features, and hence has poor sample complexity for learning many classes of functions including sparse polynomials. Recent works have thus aimed to identify se…

            Organizer

            N2
            N2

            NeurIPS 2022

            Account · 952 followers

            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

            Opening remarks - Senior Program Chair
            13:12

            Opening remarks - Senior Program Chair

            Konstantina Palla

            N2
            N2
            NeurIPS 2022 2 years ago

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

            A generalist Agent
            17:41

            A generalist Agent

            Scott Reed, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            A Unified Framework for Deep Symbolic Regression
            04:55

            A Unified Framework for Deep Symbolic Regression

            Mikel Landajuela, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Physical Data Model for Machine Learning Imaging Pipelines
            10:34

            Physical Data Model for Machine Learning Imaging Pipelines

            Marco Aversa, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Learning Tractable Probabilistic Models from Inconsistent Local Estimates
            04:32

            Learning Tractable Probabilistic Models from Inconsistent Local Estimates

            Shasha Jin, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Modern Hopfield Networks
            47:04

            Modern Hopfield Networks

            Sepp Hochreiter

            N2
            N2
            NeurIPS 2022 2 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 2022