senooken JP Social
  • FAQ
  • Login
senooken JP Socialはsenookenの専用分散SNSです。
  • Public

    • Public
    • Network
    • Groups
    • Popular
    • People

Conversation

Notices

  1. Akionux (akionux@status.akionux.net)'s status on Thursday, 29-Jul-2021 18:13:37 JST Akionux Akionux
    Useful Algorithms That Are Not Optimized By Jax, PyTorch, or Tensorflow - Stochastic Lifestyle - https://status.akionux.net/url/935433
    In conversation Thursday, 29-Jul-2021 18:13:37 JST from status.akionux.net permalink

    Attachments

    1. Domain not in remote thumbnail source whitelist: www.stochasticlifestyle.com
      Useful Algorithms That Are Not Optimized By Jax, PyTorch, or Tensorflow - Stochastic Lifestyle
      from Christopher Rackauckas
      In some previous blog posts we described in details how one can generalize automatic differentiation to give automatically stability enhancements and all sorts of other niceties by incorporating graph transformations into code generation. However, one of the things which we didn't go into too much is the limitation of these types of algorithms. This limitation is what we have termed "quasi-static" which is the property that an algorithm can be reinterpreted as some static algorithm. It turns out that for very fundamental reasons, this is the same limitation that some major machine learning frameworks impose on the code that they can fully optimize, such as Jax or Tensorflow. This led us to the question: are there algorithms which are not optimizable within this mindset, and why? The answer is now published at ICML 2021, so lets dig into ... READ MORE

    Feeds

    • Activity Streams
    • RSS 2.0
    • Atom
    • Help
    • About
    • FAQ
    • TOS
    • Privacy
    • Source
    • Version
    • Contact

    senooken JP Social is a social network, courtesy of senooken. It runs on GNU social, version 2.0.2-beta0, available under the GNU Affero General Public License.

    Creative Commons Attribution 3.0 All senooken JP Social content and data are available under the Creative Commons Attribution 3.0 license.