Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Eliminating the Invariance on the Loss Landscape of Linear Autoencoders
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-011-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-011-alpha.b-cdn.net
      • sl-yoda-v3-stream-011-beta.b-cdn.net
      • 1150868944.rsc.cdn77.org
      • 1511650057.rsc.cdn77.org
      • Subtitles
      • Off
      • en
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Eliminating the Invariance on the Loss Landscape of Linear Autoencoders
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Eliminating the Invariance on the Loss Landscape of Linear Autoencoders

            Jul 12, 2020

            Speakers

            RO

            Reza Oftadeh

            Speaker · 0 followers

            JS

            Jiayi Shen

            Speaker · 0 followers

            DS

            Dylan Shell

            Speaker · 0 followers

            About

            In this paper, we propose a new loss function for linear autoencoders (LAEs) and then analytically identify the structure of the loss surface. Optimizing the conventional Mean Square Error (MSE) loss results in a decoder matrix that spans the principal subspace of the sample covariance of the data, but fails to identify the exact eigenvectors. This shortcoming originates from an invariance that cancels out in the global map. Here, we prove that our loss function eliminates this issue, i.e., the…

            Organizer

            I2
            I2

            ICML 2020

            Account · 2.7k followers

            Categories

            Mathematics

            Category · 2.4k presentations

            About ICML 2020

            The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

            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

            One Size Fits All: Can We Train One Denoiser for All Noise Levels?
            14:34

            One Size Fits All: Can We Train One Denoiser for All Noise Levels?

            Abhiram Gnanasambandam, …

            I2
            I2
            ICML 2020 5 years ago

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

            Kernel interpolation with continuous volume sampling
            15:29

            Kernel interpolation with continuous volume sampling

            Ayoub Belhadji, …

            I2
            I2
            ICML 2020 5 years ago

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

            Poster #15

            Emily McWuillin

            I2
            I2
            ICML 2020 5 years ago

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

            Towards Understanding the Dynamics of the First-Order Adversaries
            11:04

            Towards Understanding the Dynamics of the First-Order Adversaries

            Zhun Deng, …

            I2
            I2
            ICML 2020 5 years ago

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

            Reinforcement Learning for Integer Programming: Learning to Cut
            14:55

            Reinforcement Learning for Integer Programming: Learning to Cut

            Yunhao Tang, …

            I2
            I2
            ICML 2020 5 years ago

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

            Invited Talk 4 Q&A

            Sanjiv Kumar

            I2
            I2
            ICML 2020 5 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 2020