Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Semi-Autoregressive Energy Flows: Likelihood-Free Training of Normalizing Flows
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-001-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-001-alpha.b-cdn.net
      • sl-yoda-v2-stream-001-beta.b-cdn.net
      • 1824830694.rsc.cdn77.org
      • 1979322955.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
            Semi-Autoregressive Energy Flows: Likelihood-Free Training of Normalizing Flows
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Semi-Autoregressive Energy Flows: Likelihood-Free Training of Normalizing Flows

            Jul 24, 2023

            Speakers

            PS

            Phillip Si

            Speaker · 0 followers

            ZC

            Zeyi Chen

            Speaker · 0 followers

            SSS

            Subham Sekhar Sahoo

            Speaker · 0 followers

            About

            Normalizing flows are a popular approach for constructing probabilistic and generative models. However, maximum likelihood training of flows is challenging due to the need to calculate computationally expensive determinants of Jacobians. This paper takes steps towards addressing this challenge by introducing objectives and model architectures for determinant-free training of flows. Central to our framework is the energy objective, a multidimensional extension of proper scoring rules that admits…

            Organizer

            I2
            I2

            ICML 2023

            Account · 9 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

            SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot
            04:58

            SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot

            Elias Frantar, …

            I2
            I2
            ICML 2023 2 years ago

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

            CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling
            04:02

            CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling

            Jun Zhang, …

            I2
            I2
            ICML 2023 2 years ago

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

            Charting the Course: A Deep Dive into the Evolution and Future Trajectory of Multimodal AI in Radiology
            28:20

            Charting the Course: A Deep Dive into the Evolution and Future Trajectory of Multimodal AI in Radiology

            Judy Wawira

            I2
            I2
            ICML 2023 2 years ago

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

            Sparse Learning of Dynamical Systems in RKHS: An Operator-Theoretic Approach
            05:03

            Sparse Learning of Dynamical Systems in RKHS: An Operator-Theoretic Approach

            Boya Hou, …

            I2
            I2
            ICML 2023 2 years ago

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

            Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement
            04:34

            Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement

            Eden Saig, …

            I2
            I2
            ICML 2023 2 years ago

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

            Are Large Kernels  Better Teachers than Transformers for ConvNets?
            05:18

            Are Large Kernels Better Teachers than Transformers for ConvNets?

            Tianjin Huang, …

            I2
            I2
            ICML 2023 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 ICML 2023