🤖 How can humans and AI models collaborate effectively in decision-making? Join Penn Prof. Aaron Roth on April 11 at 11AM ET for our next Vector Distinguished Lecture, where we’ll explore tractable agreement protocols that go beyond classical Bayesian assumptions. Learn about: +

Its interesting to see OpenAI slowly tighten the guardrails around the Studio Ghibli meme.

Looking forward to visiting Vector in a week and a half

TheoryML twitter: Where can I find a reference for the sequential fat shattering dimension of norm bounded linear functions in d dimensions?

Wow! arxiv.org/abs/2504.09096

Amazing. In *two* minutes, Pete Buttigieg got Andrew Shulz to see why government research is necessary. That is why these conversations matter. A lot of the hosts & audience would never hear a message like this one. But when they do, it makes sense.

Worth looking at arxiv.org/abs/2504.18395

seems like a good time to re-up these Aaron Roth notes on Adaptive Data Analysis 😉 adaptivedataanalysis.com/lecture-schedu…

Check out the terrific set of EC 2025 accepted papers! ec25.sigecom.org/program/accept…

America cannot long remain free, nor first among nations, if it becomes the kind of place where universities are dismantled because they don't align politically with the current head of the government.