00:00:00 / 00:00:00

Trade-offs in Distributed Learning

By Ohad Shamir

Appears in collection : Schlumberger workshop - Computational and statistical trade-offs in learning

In many large-scale applications, learning must be done on training data which is distributed across multiple machines. This presents an important challenge, with multiple trade-offs between optimization accuracy, statistical performance, communication cost, and computational complexity. In this talk I'll describe some recent and upcoming results about distributed convex learning and optimization, including algorithms as well as fundamental performance barriers.

Information about the video

  • Date of recording 22/03/2016
  • Date of publication 26/03/2016
  • Institution IHES
  • Format MP4

Domain(s)

Last related questions on MathOverflow

You have to connect your Carmin.tv account with mathoverflow to add question

Ask a question on MathOverflow




Register

  • Bookmark videos
  • Add videos to see later &
    keep your browsing history
  • Comment with the scientific
    community
  • Get notification updates
    for your favorite subjects
Give feedback