Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-001-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-001-alpha.b-cdn.net
      • sl-yoda-v2-stream-001-beta.b-cdn.net
      • 1824830694.rsc.cdn77.org
      • 1979322955.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
            General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds

            Dez 6, 2021

            Sprecher:innen

            HZ

            Haixiang Zhang

            Sprecher:in · 0 Follower:innen

            YB

            Yingjie Bi

            Sprecher:in · 0 Follower:innen

            JL

            Javad Lavaei

            Sprecher:in · 0 Follower:innen

            Über

            This paper considers the global geometry of general low-rank minimization problems via the Burer-Monterio factorization approach. For the rank-1 case, we prove that there is no spurious second-order critical point for both symmetric and asymmetric problems if the rank-2 RIP constant δ is less than 1/2. Combining with a counterexample with δ=1/2, we show that the derived bound is the sharpest possible. For the arbitrary rank-r case, the same property is established when the rank-2r RIP constant δ…

            Organisator

            N2
            N2

            NeurIPS 2021

            Konto · 1,9k Follower:innen

            Über 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.

            Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!

            Professionelle Aufzeichnung und Livestreaming – weltweit.

            Freigeben

            Empfohlene Videos

            Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind

            Neuro-Logic and Differentiable Controls
            26:03

            Neuro-Logic and Differentiable Controls

            Yejin Choi

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Predicting Atlantic Multidecadal Variability
            09:02

            Predicting Atlantic Multidecadal Variability

            Glenn Liu, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Systematic Generalization with Edge Transformers
            10:58

            Systematic Generalization with Edge Transformers

            Leon Bergen, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            A Procedural World Generation Framework for Systematic Evaluation of Continual Learning
            05:07

            A Procedural World Generation Framework for Systematic Evaluation of Continual Learning

            Timm Hess, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Proper Value Equivalence
            11:59

            Proper Value Equivalence

            Christopher Grimm, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Quantifying Model Predictive Uncertainty with Perturbation Theory
            05:02

            Quantifying Model Predictive Uncertainty with Perturbation Theory

            Rishabh Singh, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Interessiert an Vorträgen wie diesem? NeurIPS 2021 folgen