Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: A Damped Newton Method Achieves Global 𝒪(1/k^2) and Local Quadratic Convergence Rate
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-003-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-003-alpha.b-cdn.net
      • sl-yoda-v2-stream-003-beta.b-cdn.net
      • 1544410162.rsc.cdn77.org
      • 1005514182.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
            A Damped Newton Method Achieves Global 𝒪(1/k^2) and Local Quadratic Convergence Rate
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            A Damped Newton Method Achieves Global 𝒪(1/k^2) and Local Quadratic Convergence Rate

            Nov 28, 2022

            Speakers

            SH

            Slavomír Hanzely

            Sprecher:in · 0 Follower:innen

            DK

            Dmitry Kamzolov

            Sprecher:in · 0 Follower:innen

            DP

            Dmitry Pasechnyuk

            Sprecher:in · 0 Follower:innen

            About

            In this paper, we present the first stepsize schedule for Newton method resulting in fast global and local convergence guarantees. In particular, we a) prove an 𝒪( 1/k^2) global rate, which matches the state-of-the-art global rate of cubically regularized Newton method of Polyak and Nesterov (2006) and of regularized Newton method of Mishchenko (2021), and the later variant of Doikov and Nesterov (2021), b) prove a local quadratic rate, which matches the best-known local rate of second-order me…

            Organizer

            N2
            N2

            NeurIPS 2022

            Konto · 961 Follower:innen

            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

            Low-Rank Modular Reinforcement Learning via Muscle Synergy
            04:59

            Low-Rank Modular Reinforcement Learning via Muscle Synergy

            Heng Dong, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms
            04:58

            Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms

            Paavo Parmas, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Contact-aware Human Motion Forecasting
            01:02

            Contact-aware Human Motion Forecasting

            Wei Mao, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Sparse Additive Gaussian Processes
            04:59

            Sparse Additive Gaussian Processes

            Hengrui Luo, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            FreGAN: Exploiting Frequency Components for Training GANs under Limited Data
            05:08

            FreGAN: Exploiting Frequency Components for Training GANs under Limited Data

            Mengping Yang, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            SurDis: A Surface Discontinuity Dataset for Wearable Technology to Assist Blind Navigation in Urban Environments
            05:36

            SurDis: A Surface Discontinuity Dataset for Wearable Technology to Assist Blind Navigation in Urban Environments

            Kuan Yew Leong, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Interested in talks like this? Follow NeurIPS 2022