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

            Who Leads and Who Follows in Strategic Classification?
            13:54

            Who Leads and Who Follows in Strategic Classification?

            Tijana Zrnic, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Continuous-Time Edge Modelling using Nonparametric Point Processes
            09:21

            Continuous-Time Edge Modelling using Nonparametric Point Processes

            Xuhui Fan

            N2
            N2
            NeurIPS 2021 3 years ago

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

            TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
            13:21

            TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning

            Minchao Wu, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Robust and Decomposable Average Precision for Image Retrieval
            08:13

            Robust and Decomposable Average Precision for Image Retrieval

            Elias Ramzi, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            KeSpeech: An Open Source Speech Dataset of Mandarin and Its Eight Subdialects
            04:27

            KeSpeech: An Open Source Speech Dataset of Mandarin and Its Eight Subdialects

            Zhiyuan Tang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            What can linearized neural networks actually say about generalization?
            09:46

            What can linearized neural networks actually say about generalization?

            Guillermo Ortiz-Jiménez, …

            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