🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

CDS researchers Florentin Guth, Sanae Lotfi, and recent grad Zahra Kadkhodaie, et al, are leading a new approach to studying deep learning at #NeurIPS2024. Their workshop (Scientific Methods for Understanding Deep Learning) promotes a science of controlled experiments to understand deep nets. nyudatascience.medium.com/the-missing-mi…

📢 The workshop on Scientific Methods for Understanding Deep Learning is happening on Sunday in West meeting rooms 205-207 at #NeurIPS2024! We can't wait for Sunday! 🤩 Useful links below ⬇️

We are in West meeting rooms 205-207 at #NeurIPS2024 and our workshop is starting with some words from Zahra Kadkhodaie about the motivation for our workshop and the scientific study of DL

Program is starting hot with Tom Goldstein unravelling the mysteries of scaling up test-time compute!

Now onto Surya Ganguli talk, investigating the creativity in diffusion models, i.e. why do diffusion models fail to learn the score function and why it's a good thing.

Can LLMs plan? The answer might be in Hanie Sedghi's talk. Only one way to know, join us in West meeting rooms 205-207

Poster session still going on in West meeting rooms 205-207! Come say hi and check your favorite posters (also there is decaf)

Graduate students and advanced undergraduates: Interested in a 3-month summer research internship in Computational Neuroscience Flatiron CCN Come join us in June! Application deadline 17 Jan 2025: apply.interfolio.com/159680

When x and y are independent random variables, their joint cumulative dist function (CDF) is the product of the individual CDFs: F(x, y) - F(x)*F(y) = 0 If x,y are only uncorrelated, then Cov(x,y) =0. Can we express uncorrelated-ness in terms of the CDFs as well? Yes. This is

🌈 I'll be presenting our JMLR paper "A rainbow in deep network black boxes" today at 3pm at #ICLR25! Come to poster #334 if you're interested, I'll be happy to chat More details in the quoted thread (two levels deep)

Jonathan Pillow Tweedie’s formula wasn’t published by Tweedie (AFAIK). It was published by Miyasawa in 1961: Miyasawa, K. (1961). An empirical Bayes estimator of the mean of a normal population. Bull. Inst. Int’l Statistics, vol 38, 181-188. 1/2