Next
Afternoon poster spotlight
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Invited Talk: Understanding the Role of Optimism in Minimax Optimization: A Proximal Point Approach
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-010-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-010-alpha.b-cdn.net
      • sl-yoda-v3-stream-010-beta.b-cdn.net
      • 1973458391.rsc.cdn77.org
      • 1785266212.rsc.cdn77.org
      • Subtitles
      • Off
      • English (auto-generated)
      • English (United States)
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Invited Talk: Understanding the Role of Optimism in Minimax Optimization: A Proximal Point Approach
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Invited Talk: Understanding the Role of Optimism in Minimax Optimization: A Proximal Point Approach

            Dec 14, 2019

            Speakers

            AM

            Aryan Mokhtari

            Speaker · 0 followers

            About

            In this talk, we consider solving saddle point problems, and, in particular, we discuss the concept of “optimism” or “negative momentum” - a technique which is observed to have superior empirical performance in training GANs. The goal of this talk is to provide a theoretical understanding on why optimism helps, in particular why the Optimistic Gradient Descent Ascent (OGDA) algorithm performs well in practice. To do so, we first consider the classical Proximal Point algorithm which is an implici…

            Organizer

            N2
            N2

            NIPS 2019

            Account · 98 followers

            Categories

            AI & Data Science

            Category · 10.8k presentations

            Mathematics

            Category · 2.4k presentations

            About NIPS 2019

            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.

            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

            Theory Panel Discussion
            30:31

            Theory Panel Discussion

            Florent Krzakala, …

            N2
            N2
            NIPS 2019 5 years ago

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

            A sleep-wake detection algorithm for memory-constrained wearable devices: Change Point Decoder
            09:54

            A sleep-wake detection algorithm for memory-constrained wearable devices: Change Point Decoder

            Ayse Cakmak

            N2
            N2
            NIPS 2019 5 years ago

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

            Challenges For Meta and Continual Reinforcement Learning
            30:31

            Challenges For Meta and Continual Reinforcement Learning

            Raia Hadsell

            N2
            N2
            NIPS 2019 5 years ago

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

            Large-scale classification of breast MRI exams using deep convolutional networks
            12:23

            Large-scale classification of breast MRI exams using deep convolutional networks

            Shizhan Gong

            N2
            N2
            NIPS 2019 5 years ago

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

            How I Fall In Writing Papers
            13:24

            How I Fall In Writing Papers

            Veronika Cheplygina

            N2
            N2
            NIPS 2019 5 years ago

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

            Invited talk: Neuro-symbolic knowledge representation
            31:10

            Invited talk: Neuro-symbolic knowledge representation

            William Cohen

            N2
            N2
            NIPS 2019 5 years ago

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

            Interested in talks like this? Follow NIPS 2019