Guodong Zhang.

@Guodzh

PhD student . Machine learning.

Toronto, Ontario
Vrijeme pridruživanja: svibanj 2016.

Tweetovi

Blokirali ste korisnika/cu @Guodzh

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @Guodzh

  1. Prikvačeni tweet
    9. srp 2019.

    New paper on studying how the critical batch size changes based on properties of the optimization algorithm (including momentum and preconditioning), through two different lenses: large scale experiments, and analysis of a simple noisy quadratic model.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    30. sij

    John Schulman's opinionated guide to ML research

    Poništi
  3. proslijedio/la je Tweet
    26. sij

    Kobe was a legend on the court and just getting started in what would have been just as meaningful a second act. To lose Gianna is even more heartbreaking to us as parents. Michelle and I send love and prayers to Vanessa and the entire Bryant family on an unthinkable day.

    Poništi
  4. 26. sij

    Plz tell me it’s not true!!!!!!!

    Poništi
  5. 26. sij
    Poništi
  6. proslijedio/la je Tweet
    23. sij

    Looking to do a PhD/Postdoc at the intersection of and ? Drop me a line - we are hiring in Berlin, Germany. Also looking to grow our solver dev team. RT welcome.

    Poništi
  7. proslijedio/la je Tweet
    22. sij

    FixMatch: focusing on simplicity for semi-supervised learning and improving state of the art (CIFAR 94.9% with 250 labels, 88.6% with 40). Collaboration with Kihyuk Sohn, Nicholas Carlini

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    17. sij

    I've spent weeks reading FATE postdoc and intern apps, and all I can think is 1) I'm so optimistic about the future of this research area given all the amazing, passionate, interdisciplinary young researchers doing great work, and 2) seriously, people, make a research website!

    Poništi
  9. 30. pro 2019.

    It is even harder for international students. 😶

    Poništi
  10. proslijedio/la je Tweet
    24. pro 2019.
    Odgovor korisnicima

    Yes. This is probably what you want!

    Poništi
  11. proslijedio/la je Tweet
    19. pro 2019.

    Finally ...... our paper on "foresight pruning" just got accepted by . We introduced a simple, yet effective pruning criterion for pruning networks before training and related the criterion to recent NTK analysis.

    Prikaži ovu nit
    Poništi
  12. 19. pro 2019.

    Joint work with Chaoqi and .

    Prikaži ovu nit
    Poništi
  13. 19. pro 2019.

    Finally ...... our paper on "foresight pruning" just got accepted by . We introduced a simple, yet effective pruning criterion for pruning networks before training and related the criterion to recent NTK analysis.

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    14. pro 2019.

    Presenting joint work with and Jimmy () at bridging game theory and deep learning workshop

    Poništi
  15. proslijedio/la je Tweet
    13. pro 2019.

    Graph representation learning is the most popular workshop of the day at . Amazing how far the field has advanced. I did not imagine so many people would get into this when I started working on graph neural nets back in 2015 during an internship. Time flies...

    Poništi
  16. proslijedio/la je Tweet
    12. pro 2019.

    Tomorrow 8:40am I will share my thoughts on evaluating epistemic uncertainty at Bayesian deep learning workshop. Also come to discuss with me at poster (in-between uncertainty work with and Rich Turner) & panel session 😆

    Prikaži ovu nit
    Poništi
  17. 11. pro 2019.

    Roger is really a knowledgeable person and has very deep understanding about deep learning and general machine learning. I learnt a lot from him in the past two years, I believe you will too.

    Poništi
  18. proslijedio/la je Tweet
    11. pro 2019.

    Come speak with us about posterior collapse in VAEs! (In 30 minutes...)

    Poništi
  19. 9. pro 2019.

    It's nice to see reviving interests in EBM. My first project in machine learning was actually training a hybrid model combining classifier and EBM back to 2016. Unfortunately, I didn't get it to work well at that time. Shout out to for the success and new insights.

    Poništi
  20. 9. pro 2019.

    I forgot to mention that VOGN (by ) and NNG essentially share the same formulation and are kinda same algorithm.

    Prikaži ovu nit
    Poništi
  21. 9. pro 2019.

    Both VOGN and Noisy Natural Gradient (NNG) came out at roughly the same time.

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·