Skip to content
By using Twitter’s services you agree to our Cookies Use. We and our partners operate globally and use cookies, including for analytics, personalisation, and ads.
  • Home Home Home, current page.
  • About

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @
  • Language: English
    • Bahasa Indonesia
    • Bahasa Melayu
    • Català
    • Čeština
    • Dansk
    • Deutsch
    • English UK
    • Español
    • Filipino
    • Français
    • Hrvatski
    • Italiano
    • Magyar
    • Nederlands
    • Norsk
    • Polski
    • Português
    • Română
    • Slovenčina
    • Suomi
    • Svenska
    • Tiếng Việt
    • Türkçe
    • Ελληνικά
    • Български език
    • Русский
    • Српски
    • Українська мова
    • עִבְרִית
    • العربية
    • فارسی
    • मराठी
    • हिन्दी
    • বাংলা
    • ગુજરાતી
    • தமிழ்
    • ಕನ್ನಡ
    • ภาษาไทย
    • 한국어
    • 日本語
    • 简体中文
    • 繁體中文
  • Have an account? Log in
    Have an account?
    · Forgot password?
    New to Twitter?
    Sign up
AnimaAnandkumar's profile
Prof. Anima Anandkumar
Prof. Anima Anandkumar
Prof. Anima Anandkumar
@AnimaAnandkumar

Tweets

Prof. Anima Anandkumar

@AnimaAnandkumar

Director of #AI #research @nvidia, Bren #Professor @Caltech, Fmr Principal scientist @awscloud #Sloan fellow #Tensors Erdos #2 #dancer http://anima-ai.org 

Santa Clara, CA
tensorlab.cms.caltech.edu/users/anima/
Joined October 2014

Tweets

  • © 2020 Twitter
  • About
  • Help Center
  • Terms
  • Privacy policy
  • Imprint
  • Cookies
  • Ads info
Dismiss
Previous
Next

Go to a person's profile

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @

Promote this Tweet

Block

  • Tweet with a location

    You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more

    Your lists

    Create a new list

    Under 100 characters, optional
    Privacy

    Copy link to Tweet

    Embed this Tweet

    Embed this Video

    Add this Tweet to your website by copying the code below. Learn more

    Add this video to your website by copying the code below. Learn more

    Hmm, there was a problem reaching the server.

    By embedding Twitter content in your website or app, you are agreeing to the Twitter Developer Agreement and Developer Policy.

    Preview

    Why you're seeing this ad

    Log in to Twitter

    · Forgot password?
    Don't have an account? Sign up »

    Sign up for Twitter

    Not on Twitter? Sign up, tune into the things you care about, and get updates as they happen.

    Sign up
    Have an account? Log in »

    Two-way (sending and receiving) short codes:

    Country Code For customers of
    United States 40404 (any)
    Canada 21212 (any)
    United Kingdom 86444 Vodafone, Orange, 3, O2
    Brazil 40404 Nextel, TIM
    Haiti 40404 Digicel, Voila
    Ireland 51210 Vodafone, O2
    India 53000 Bharti Airtel, Videocon, Reliance
    Indonesia 89887 AXIS, 3, Telkomsel, Indosat, XL Axiata
    Italy 4880804 Wind
    3424486444 Vodafone
    » See SMS short codes for other countries

    Confirmation

     

    Welcome home!

    This timeline is where you’ll spend most of your time, getting instant updates about what matters to you.

    Tweets not working for you?

    Hover over the profile pic and click the Following button to unfollow any account.

    Say a lot with a little

    When you see a Tweet you love, tap the heart — it lets the person who wrote it know you shared the love.

    Spread the word

    The fastest way to share someone else’s Tweet with your followers is with a Retweet. Tap the icon to send it instantly.

    Join the conversation

    Add your thoughts about any Tweet with a Reply. Find a topic you’re passionate about, and jump right in.

    Learn the latest

    Get instant insight into what people are talking about now.

    Get more of what you love

    Follow more accounts to get instant updates about topics you care about.

    Find what's happening

    See the latest conversations about any topic instantly.

    Never miss a Moment

    Catch up instantly on the best stories happening as they unfold.

    1. Prof. Anima Anandkumar‏ @AnimaAnandkumar Mar 11
      • Report Tweet
      • Report NetzDG Violation

      Updated paper on implicit competitive regularization in #GANs https://arxiv.org/abs/1910.05852  Blog: https://f-t-s.github.io/projects/icr/  GANs work due to simultaneous optimization of generator & discriminator; not choice of divergence. With Florian Schaefer @Kay12400259 @Caltechpic.twitter.com/QwmJgJhzDZ

      2 replies 32 retweets 125 likes
      Show this thread
    2. Prof. Anima Anandkumar‏ @AnimaAnandkumar Mar 11
      • Report Tweet
      • Report NetzDG Violation

      GANs work when both agents are simultaneously updated. If one agent is fixed and other updated, performance worsens. Hence, GANs don't converge to Nash. Instead, implicit regularization from simultaneous updates is key to good performance.pic.twitter.com/jIEwOpGGwg

      1 reply 10 retweets 39 likes
      Show this thread
    3. Prof. Anima Anandkumar‏ @AnimaAnandkumar Mar 11
      • Report Tweet
      • Report NetzDG Violation

      Implicit competitive regularization in GANs encourages discriminators to learn slowly. It is more effective than explicit gradient penalties. Competitive gradient descent further strengthens this implicit reg. by using mixed Hessian to account for interaction among playerspic.twitter.com/t5yXDYYhMK

      1 reply 0 retweets 13 likes
      Show this thread
    4. Prof. Anima Anandkumar‏ @AnimaAnandkumar Mar 11
      • Report Tweet
      • Report NetzDG Violation

      Prof. Anima Anandkumar Retweeted Prof. Anima Anandkumar

      For details on competitive gradient descent, check out this threadhttps://twitter.com/AnimaAnandkumar/status/1205173860284293121?s=20 …

      Prof. Anima Anandkumar added,

      Prof. Anima Anandkumar @AnimaAnandkumar
      Florian Schafer and I have a #NeurIPS2019 poster #195 today from 10:45 to 12:45. GAN training is unstable + mode collapse. How to fix optimization in GANs? We propose competitive gradient descent: each update is a Nash equilibrium of a local game. Blog: https://f-t-s.github.io/projects/cgd/  pic.twitter.com/RinSTyKiyg
      Show this thread
      3 replies 0 retweets 30 likes
      Show this thread
    5. Mohammad Taha Toghani‏ @mttoghani Mar 12
      • Report Tweet
      • Report NetzDG Violation
      Replying to @AnimaAnandkumar

      The interpretation behind second order derivatives is really interesting in your work and the results are amazing. An optimization question: isn't CGD much slower than GD per iteration? (As I got, you compute D_{xy} which is really slow? Also, what is the case in Neural Nets?

      1 reply 0 retweets 0 likes
    6. Prof. Anima Anandkumar‏ @AnimaAnandkumar Mar 12
      • Report Tweet
      • Report NetzDG Violation
      Replying to @mttoghani

      Prof. Anima Anandkumar Retweeted Prof. Anima Anandkumar

      CGD is only twice cost of GD when mixed-mode differentiation is available, as in #JAX Further, with conjugate gradients, iteration reduces to GD when there is no instability.https://twitter.com/AnimaAnandkumar/status/1219133562651176965?s=20 …

      Prof. Anima Anandkumar added,

      Prof. Anima Anandkumar @AnimaAnandkumar
      We used JAX for competitive gradient descent (CGD) with Hessian-vector products. Mixed mode differentiation in JAX makes this efficient (just twice cost of backprop). We used CGD for training GANs and for constrained problems in RL. This library will be very useful @pierrelux https://twitter.com/hardmaru/status/1219088493583880192 …
      Show this thread
      2 replies 0 retweets 7 likes
      Prof. Anima Anandkumar‏ @AnimaAnandkumar Mar 12
      • Report Tweet
      • Report NetzDG Violation
      Replying to @AnimaAnandkumar @mttoghani

      Our current @PyTorch implementation for CGD is also quite fasthttps://github.com/devzhk/Implicit-Competitive-Regularization …

      10:11 PM - 12 Mar 2020
      • 1 Like
      • Mohammad Taha Toghani
      1 reply 0 retweets 1 like
        1. Mohammad Taha Toghani‏ @mttoghani Mar 12
          • Report Tweet
          • Report NetzDG Violation
          Replying to @AnimaAnandkumar @PyTorch

          Thank you so much!

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo

      Loading seems to be taking a while.

      Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

        Promoted Tweet

        false

        • © 2020 Twitter
        • About
        • Help Center
        • Terms
        • Privacy policy
        • Imprint
        • Cookies
        • Ads info