Thanh T. Nguyen

@thanhnguyentang

"Understand the problem, understand the data, understand the objective, select good notation, and write down everything you know." - Terence Tao.

Australia
Vrijeme pridruživanja: rujan 2011.

Tweetovi

Blokirali ste korisnika/cu @thanhnguyentang

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

  1. Prikvačeni tweet
    9. lis 2019.
    Poništi
  2. proslijedio/la je Tweet

    [cs.LG] On Positive-Unlabeled Classification in GAN. (arXiv:2002.01136v1 [cs.LG]) This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the traini…

    Poništi
  3. proslijedio/la je Tweet
    prije 8 sati

    Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise.

    Poništi
  4. proslijedio/la je Tweet
    prije 6 sati

    Learning Task-Driven Control Policies via Information Bottlenecks.

    Poništi
  5. proslijedio/la je Tweet

    "Earn with your mind, not your time." — 

    Poništi
  6. Try to finish unimportant but urgent tasks soon so that you can have more time thinking on important problems

    Poništi
  7. proslijedio/la je Tweet
    4. velj

    Designing GANs: A Likelihood Ratio Approach.

    Poništi
  8. proslijedio/la je Tweet

    Limit Distribution Theory for Smooth Wasserstein Distance with Applications to Generative Modeling.

    Poništi
  9. proslijedio/la je Tweet
    prije 9 sati

    "RL, DL, and the role of policy gradient methods" by Sham Kakade via

    Poništi
  10. proslijedio/la je Tweet
    4. velj

    Stochastic geometry to generalize the Mondrian Process.

    Poništi
  11. 4. velj

    This is one of many factors I should move across from Pacific to North American soon :(

    Poništi
  12. proslijedio/la je Tweet
    4. velj

    Effective Diversity in Population-Based Reinforcement Learning.

    Poništi
  13. proslijedio/la je Tweet
    4. velj

    Revisiting Meta-Learning as Supervised Learning.

    Poništi
  14. proslijedio/la je Tweet
    4. velj

    Thompson Sampling Algorithms for Mean-Variance Bandits.

    Poništi
  15. proslijedio/la je Tweet
    4. velj

    A Corrective View of Neural Networks: Representation, Memorization and Learning.

    Poništi
  16. proslijedio/la je Tweet
    4. velj

    new paper on adversarial linear contextual bandits! feat. one of the first practical algorithms that can handle model misspecification + the first one to achieve optimal regret in an adversarial contextual bandit problem. w/ my student Julia Olkhovskaya

    Poništi
  17. proslijedio/la je Tweet
    4. velj

    On the Information Bottleneck Problems: Models, Connections, Applications and Information Theoretic Views.

    Poništi
  18. proslijedio/la je Tweet
    2. velj

    “At Tesla, using AI to solve self-driving isn’t just icing on the cake, it the cake” - Join AI at Tesla! It reports directly to me & we meet/email/text almost every day. My actions, not just words, show how critically I view (benign) AI.

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    3. velj

    Tesla AI recruitment 🔥 “A PhD is definitely not required. All that matters is a deep understanding of AI and ability to implement NNs in a way that is actually useful (latter point is what’s truly hard). Don’t care if you finished high school.”

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    3. velj

    Stable Prediction with Model Misspecification and Agnostic Distribution Shift. (arXiv:2001.11713v1 [cs.LG])

    Poništi
  21. proslijedio/la je Tweet
    1. velj

    Also, check out the ALT 2020 proceedings at:

    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:

    ·