Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-012-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-012-alpha.b-cdn.net
      • sl-yoda-v3-stream-012-beta.b-cdn.net
      • 1338956956.rsc.cdn77.org
      • 1656830687.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
            CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator

            Dec 6, 2021

            Speakers

            AD

            Alek Dimitriev

            Speaker · 0 followers

            MZ

            Mingyuan Zhou

            Speaker · 0 followers

            About

            Accurately backpropagating the gradient through categorical variables is a challenging task that arises in various domains, such as training discrete latent variable models. To this end, we propose CARMS, an unbiased estimator for categorical random variables based on multiple mutually negatively correlated (jointly antithetic) samples. CARMS combines REINFORCE with copula based sampling to avoid duplicate samples and reduce the variance, while keeping the estimator unbiased using a simple multi…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 1.9k followers

            About 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.

            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

            Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning
            05:06

            Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning

            Utkarsh A. Mishra, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients
            13:13

            SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients

            Feihu Huang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Asymptotically Best Causal Effect Identification with Multi-Armed Bandits!
            13:52

            Asymptotically Best Causal Effect Identification with Multi-Armed Bandits!

            Alan Malek, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Dynabench: Rethinking Benchmarking in AI
            19:41

            Dynabench: Rethinking Benchmarking in AI

            Douwe Kiela

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Designing Molecular Models with Machine Learning and Experimental Data
            19:27

            Designing Molecular Models with Machine Learning and Experimental Data

            Cecilia Clementi

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations
            11:16

            Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations

            Shasha Li, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Interested in talks like this? Follow NeurIPS 2021