Gavin Brown

The net effect of strong LLMs will be to make it easier to find information and learn.

Dimensional lumber is out.

Distributional lumber is in.

If δ=0, we write ε-DP and call it “pure” DP. If δ>0, we call it “unclean.”

I wrote a survey article on computationally efficient methods for "robust" mean estimation, including robustness to contamination, heavy-tailed data, or in the sense of differential privacy.

The same ideas are useful for all 3 (seemingly-different) forms of robustness! 1/2
arxiv.org/abs/2412.02670

It’s bad when reviewers are extremely wrong, but it feels worse when they’re extremely right.

No idea. I never let reality constrain my jokes.

Instead of a special poster session, NeurIPS should use physical spotlights to identify exceptional work.

Excellent: “Energetic Aliens”

stephenmalina.com/post/2021-07...

Good point, I’ll try to keep quiet about my opinions on the word “epoch.”

Can I still join if I pronounce it “click”?

The issue is: important things need short names.

I know! “Erasure,” come on.

Review: Serious issues with presentation meant I could not interpret the results.

Rebuttal: Great, you’re saying we made a breakthrough and just need to write it up better.

Words matter: Alternatives for charged terminology in the computing profession ACM’s efforts to combat exclusion in the computing profession, ACM's Diversity and Inclusion Council has launched "Words Matter," an effort to replace offensive or exclusionary terminology in the comp...

ACM guidelines, at least currently, also suggest avoiding “Byzantine.”

www.acm.org/diversity-in...

Ceci n'est pas une Annoucement Sign.

“We went to a restaurant once, and it made a huge impression on us.”

And, once in a while, as you’re cleaning up the proof of your upper bound, you have to stop and ask “wait, is this even an algorithm?”

William Sealy Gosset developed the Student’s t-test as part of his work as Head Brewer of Guiness.

Pearson was already working with big data.

A few of us are going to corner the market on efficient differentially private mean estimation in Mahalanobis norm, really drive up the price.

Never ask a learning theorist about their algorithm’s run time. If it’s good, they’ll bring it up themselves.

I seem to recall that math undergrads in the US have approximate gender parity. What are they doing right that CS does wrong?

Not a big fan of things changing. I’m still secretly hoping everyone will get back on AIM and Xanga.