Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Constructive universal high-dimensional distribution generation through deep ReLU networks
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-014-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-014-alpha.b-cdn.net
      • sl-yoda-v3-stream-014-beta.b-cdn.net
      • 1978117156.rsc.cdn77.org
      • 1243944885.rsc.cdn77.org
      • Subtitles
      • Off
      • en
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Constructive universal high-dimensional distribution generation through deep ReLU networks
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Constructive universal high-dimensional distribution generation through deep ReLU networks

            Jul 12, 2020

            Speakers

            DP

            Dmytro Perekrestenko

            Speaker · 0 followers

            SM

            Stephan Müller

            Speaker · 0 followers

            HB

            Helmut Bölcskei

            Speaker · 0 followers

            About

            We present an explicit deep network construction that transforms uniformly distributed one-dimensional noise into an arbitrarily close approximation of any two-dimensional target distribution of finite differential entropy and Lipschitz-continuous pdf. The key ingredient of our design is a generalization of the "space-filling” property of sawtooth functions introduced in (Bailey Telgarsky, 2018). We elicit the importance of depth in our construction in driving the Wasserstein distance between th…

            Organizer

            I2
            I2

            ICML 2020

            Account · 2.7k followers

            Categories

            Mathematics

            Category · 2.4k presentations

            AI & Data Science

            Category · 10.8k presentations

            About ICML 2020

            The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

            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

            Graph Homomorphism Convolution
            16:07

            Graph Homomorphism Convolution

            Hoang Nguyen, …

            I2
            I2
            ICML 2020 5 years ago

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

            DeepMind at WiML Un-worskhop
            14:38

            DeepMind at WiML Un-worskhop

            Meire Fortunato

            I2
            I2
            ICML 2020 5 years ago

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

            Healing Products of Gaussian Process Experts
            15:43

            Healing Products of Gaussian Process Experts

            Samuel Cohen, …

            I2
            I2
            ICML 2020 5 years ago

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

            Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
            15:12

            Skew-Fit: State-Covering Self-Supervised Reinforcement Learning

            Vitchyr Pong, …

            I2
            I2
            ICML 2020 5 years ago

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

            Interpretable End-to-end Autonomous Driving with Reinforcement Learning
            02:57

            Interpretable End-to-end Autonomous Driving with Reinforcement Learning

            Jianyu Chen, …

            I2
            I2
            ICML 2020 5 years ago

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

            Normalisr: inferring single-cell differential and co-expression with linear association testing
            05:19

            Normalisr: inferring single-cell differential and co-expression with linear association testing

            Lingfei Wang

            I2
            I2
            ICML 2020 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 ICML 2020