←
Aaron Roth4,060 posts
Aaron Roth avatar

Aaron Roth

@Aaroth

CS prof at Penn. Researcher at Resolution. Author of The Ethical Algorithm (w/ Michael Kearns). I study ML, alignment, game theory, and uncertainty.

◷ Joined May 2007▧ 292 Photos and videos
Aaron Roth avatar
Aaron Roth@Aaroth·Nov 13

I had Codex formalize our randomized calibrated multiaccuracy upper bound --- it now has a lean proof. Really very easy.

🚀 STOC 2027, a flagship conference in theoretical computer science, made all 1,665 submissions publicly available. So we launched the STOC 2027 Formalization Initiative on Prove2Me! Our AI agents have translated the main theorems and supporting lemmas of 1,496 submissions into Lean 4 statements! Some already have completed proof formalizations, with many more awaiting contributions. You don't need to know Lean or fully understand the underlying mathematics to get started! If you know how to work with AI agents, you can help formalize proofs. We invite authors, researchers, and the broader community to explore these formalized statements, check them against the original papers, and contribute proof formalizations! 📊 Explore the initiative: stoc2027formalization.vercel… 🤝 Contribute proof formalizations: prove2.me/collections/acm-st…

Post attachment
Barna Saha avatar
⟳ Aaron Roth retweeted
Barna Saha@B1ar2n3a·Nov 7

If you are at New York tomorrow, come to TCS+AI workshop. The floor will be hot 😁.

Looking forward to tomorrow's TCS+AI Workshop at FOCS. @littmath will give a keynote, followed by a panel discussion with Dan Spielman, @littmath, @praveshkkothari, @B1ar2n3a, and Nikhil Srivastava. I'll moderate. Come with all of your questions, anxieties, and hopes!

Michal Feldman avatar
⟳ Aaron Roth retweeted
Michal Feldman@MichalFeldman9·Nov 4

🥁 Very happy to announce that ACM EC'27 will take place on July 12–16, 2027, at Northwestern University, Chicago. ▪️General Chair: Jason Hartline ▪️Program Committee Chairs: Annie Liang and Grant Schoenebeck Looking forward to seeing many of you there! @AcmSIGecom

Aaron Roth avatar
⟳ Aaron Roth retweeted
Aaron Roth@Aaroth·Nov 3

Multicalibration is useful for lots of stuff - omniprediction, fast agreement, hard core set construction - but often overkilll. For these applications you only need global calibration, plus multiaccuracy. But does calibrated multiaccuracy actually require fewer samples to learn?

Post attachment
Aaron Roth avatar
Aaron Roth@Aaroth·Nov 3

Woah, thats a lot of papers. Tired of the rat race? FORC that! THe first deadline is coming up, Nov 11: responsiblecomputing.org/for…

STOC 2027 received 1665 submissions. In a bold new experiment, all submissions (and author identities) are immediately made public. This is the most immediate and revealing posting of any conference I am aware of. Take a look and see what you find! stoc2027.sigact-ec.workers.d…

Aaron Roth avatar
Aaron Roth@Aaroth·Nov 3

In particular, randomization isn't needed for the closely related problem of multicalbation. But for calibrated multiaccuracy, there is a sharp polynomial separation between the minimax sample complexity when the model is constrained to be deterministic compared to when its not.

Aaron Roth avatar
Aaron Roth@Aaroth·Nov 3

The answer is yes - at least if you don't have too many groups (otherwise no). But surprisingly the sample complexity depends on if you allow your model to randomize at test time! Thats kind of weird; most single distribution learning problems don't require randomization.

Post attachment
Aaron Roth avatar
Aaron Roth@Aaroth·Nov 2

The only thing the Agreement Theorem uses about Bayesian rationality and priors is that the "belief" at each round of conversation is calibrated conditional on the one round prior. This you can achieve efficiently, without any distributional assumptions: arxiv.org/abs/2411.19791