Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent
      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
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent

            Apr 14, 2021

            Speakers

            FK

            Fred Kunstner

            Speaker · 0 followers

            RK

            Raunak Kumar

            Speaker · 0 followers

            MS

            Mark Schmidt

            Speaker · 0 followers

            About

            Expectation maximization (EM) is the default algorithm for fitting probabilistic models with missing or latent variables, yet we lack a full understanding of its non-asymptotic convergence properties. Previous works show results along the lines of "EM converges at least as fast as gradient descent" by assuming the conditions for the convergence of gradient descent apply to EM. This approach is not only loose, in that it does not capture that EM can make more progress than a gradient step, but th…

            Organizer

            A2
            A2

            AISTATS 2021

            Account · 63 followers

            Categories

            AI & Data Science

            Category · 10.8k presentations

            About AISTATS 2021

            The 24th International Conference on Artificial Intelligence and Statistics was held virtually from Tuesday, 13 April 2021 to Thursday, 15 April 2021.

            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

            Finite-Sample Regret Bound for Distributionally Robust Policy Learning in Tabular RL
            03:02

            Finite-Sample Regret Bound for Distributionally Robust Policy Learning in Tabular RL

            Zhengqing Zhou, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Adversarially Robust Estimate and Risk Analysis in Linear Regression
            03:03

            Adversarially Robust Estimate and Risk Analysis in Linear Regression

            Yue Xing, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Kernel Interpolation for Scalable Online Gaussian Processes
            02:36

            Kernel Interpolation for Scalable Online Gaussian Processes

            Samuel Stanton, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Flow-based Alignment Approaches for Probability Measures in Different Spaces
            03:04

            Flow-based Alignment Approaches for Probability Measures in Different Spaces

            Tam Le, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Shapley Flow: A Graph-based Approach to Interpreting Model Predictions
            03:01

            Shapley Flow: A Graph-based Approach to Interpreting Model Predictions

            Jiaxuan Wang, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Gaming Helps! Learning from Strategic Interactions in Natural Dynamics
            03:33

            Gaming Helps! Learning from Strategic Interactions in Natural Dynamics

            Yahav Bechavod, …

            A2
            A2
            AISTATS 2021 4 years ago

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

            Interested in talks like this? Follow AISTATS 2021