Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
        0:00 / 0:00
        • Report Issue
        • Settings
        • Playlists
        • Bookmarks
        • Subtitles
        • Playback rate
        • Quality
        • Settings
        • Debug information
        • Server
        • Subtitles size Medium
        • Bookmarks
        • Server
        • Subtitles
        • Playback rate
        • Quality
        • Subtitles size
        • Large
        • Medium
        • Small
        • Mode
        • Video Slideshow
        • Audio Slideshow
        • Slideshow
        • Video
        My playlists
          Bookmarks
            00:00:00
              • Settings
              • Sync diff
              • Quality
              • Settings
              • Server
              • Quality
              • Server

              Estimation of Entropy in Constant Space with Improved Sample Complexity

              Nov 28, 2022

              Speakers

              MA

              Maryam Aliakbarpour

              Speaker · 0 followers

              AM

              Andrew McGregor

              Speaker · 0 followers

              JN

              Jelani Nelson

              Speaker · 2 followers

              About

              Recent work of Acharya et al. (NeurIPS 2019) showed how to estimate the entropy of a distribution 𝒟 over an alphabet of size k up to ±ϵ additive error by streaming over (k/ϵ^3) ·polylog(1/ϵ) i.i.d. samples and using only O(1) words of memory. In this work, we give a new constant memory scheme that reduces the sample complexity to (k/ϵ^2)·polylog(1/ϵ). We conjecture that this is optimal up to polylog(1/ϵ) factors.

              Organizer

              N2
              N2

              NeurIPS 2022

              Account · 952 followers

              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

              Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection
              04:59

              Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection

              Catherine Glossop, …

              N2
              N2
              NeurIPS 2022 2 years ago

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

              Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
              05:33

              Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

              Eshaan Nichani, …

              N2
              N2
              NeurIPS 2022 2 years ago

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

              Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization
              04:22

              Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

              Ali Kavis, …

              N2
              N2
              NeurIPS 2022 2 years ago

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

              Closing remarks & awards
              05:26

              Closing remarks & awards

              Arno Blaas

              N2
              N2
              NeurIPS 2022 2 years ago

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

              Amplifying Membership Exposure via Data Poisoning
              04:58

              Amplifying Membership Exposure via Data Poisoning

              Yufei Chen, …

              N2
              N2
              NeurIPS 2022 2 years ago

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

              Accelerated Training of Physics Informed Neural Networks (PINNs) using Meshless Discretizations
              04:57

              Accelerated Training of Physics Informed Neural Networks (PINNs) using Meshless Discretizations

              Ramansh Sharma, …

              N2
              N2
              NeurIPS 2022 2 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 2022