Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-016-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-016-alpha.b-cdn.net
      • sl-yoda-v3-stream-016-beta.b-cdn.net
      • 1504562137.rsc.cdn77.org
      • 1896834465.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
            Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness

            Jul 12, 2020

            Speakers

            AK

            Aounon Kumar

            Speaker · 0 followers

            AL

            Alexander Leviné

            Speaker · 0 followers

            TG

            Tom Goldstein

            Speaker · 0 followers

            About

            Randomized smoothing, using just a simple isotropic Gaussian distribution, has been shown to produce good robustness guarantees against ℓ_2-norm bounded adversaries. In this work, we show that extending the smoothing technique to defend against other attack models can be challenging, especially in the high-dimensional regime. In particular, for a vast class of i.i.d. smoothing distributions, we prove that the largest ℓ_p-radius that can be certified decreases as O(1/d^1/2 - 1/p) with dimen…

            Organizer

            I2
            I2

            ICML 2020

            Account · 2.6k 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

            System-wide Monitoring: An Explanatory Monitoring Architecture Composed of Unreliable Parts
            46:26

            System-wide Monitoring: An Explanatory Monitoring Architecture Composed of Unreliable Parts

            Leilani H. Gilpin

            I2
            I2
            ICML 2020 5 years ago

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

            Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
            05:44

            Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

            Karl Pertsch, …

            I2
            I2
            ICML 2020 5 years ago

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

            Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
            14:28

            Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning

            Esther Rolf, …

            I2
            I2
            ICML 2020 5 years ago

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

            Open Remark

            Wei-Lun (Harry) Chao

            I2
            I2
            ICML 2020 5 years ago

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

            Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge
            15:14

            Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge

            Laura Rieger, …

            I2
            I2
            ICML 2020 5 years ago

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

            Adversarial Nonnegative Matrix Factorization
            10:36

            Adversarial Nonnegative Matrix Factorization

            Lei Luo, …

            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