iiinova — where your digital self keeps evolving

Reposted by @anaymehrotra.bsky.social

Felix Zhou @felix-zhou-cfz.bsky.social · 30/05/2026

Karan and Du, followed by @haithambouammar.bsky.social et al., showed that inference-time sampling from carefully chosen distributions improves LLM reasoning; no posttraining, reward curation, or verifier needed. We show smarter test-time budget allocation yields drastic gains! (1/3)

121

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 30/11/2025

Our #NeurIPS2025 workshop “Reliable ML from Unreliable Data” schedule is live! 🎉 Talks, posters, and a panel all day, plus a best paper session (announcement coming soon 👀). Come hang out with us for the full program!

A black and white illustration of a scroll-style banner containing the text "RELIABLE ML WORKSHOP at NeurIPS'25"

141

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 28/07/2025

📣 Excited to announce the Reliable ML workshop at neuripsconf.bsky.social‬ 2025! How do we build trustworthy models under distribution shift, adversarial attacks, strategic behavior, and missing data? → Submission tracks: long (9 pg) and short (4 pg) → Deadline: Aug 22, 2025 (AOE)

reliablemlworkshop.github.io

Reliable ML from Unreliable Data — NeurIPS 2025 Workshop

120

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 15/07/2025

Slides 🪧 from our language generation tutorial are now up! Check them out at languagegeneration.github.io Recorded sessions coming – meanwhile also check out Jon's invited talk at ICML – icml.cc/virtual/2025... !

languagegeneration.github.io

Tutorial on Language Generation in the Limit

020

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 29/06/2025

If you are at COLT, join us for a tutorial on Language Generation on the first day! The tutorial dives into Kleinberg and Mullainathan’s “generation in the limit” framework and the exciting space of works building on it. 🕤 9:30 AM–12:00 PM | Room C 🔗 languagegeneration.github.io

010

Reposted by @anaymehrotra.bsky.social

let-all.com @let-all.com · 24/06/2025

📣Join us at COLT 2025 in Lyon for a community event! 📅When: Mon, June 30 | 16:00 CET What: Fireside chat w/ Peter Bartlett & Vitaly Feldman on communicating a research agenda, followed by mentorship roundtable to practice elevator pitches & mingle w/ COLT community! let-all.com/colt25.html

0156

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 11/06/2025

We are organizing a Language Generation tutorial @ #COLT 2025! Visit our website (languagegeneration.github.io/) for references and materials; content updated regularly, check back for the latest! Coorganizers: Moses Charikar, Chirag Pabbaraju, Charlotte Peale, Grigoris Velegkas See you in Lyon!

languagegeneration.github.io

Tutorial on Language Generation in the Limit

010

Reposted by @anaymehrotra.bsky.social

Clément Canonne @ccanonne.github.io · 10/05/2025

The tutorials, workshops, and community events for #COLT2025 have been announced! Exciting topics, and impressive slate of speakers and events, on June 30! The workshops have calls for contributions (⏰ May 16, 19, and 25): check them out! learningtheory.org/colt2025/ind...

Community events and tutorials, list from the website

2197

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 09/05/2025

@felix-zhou-cfz.bsky.social is giving two talks about this work at @uwaterloo.ca – one in the A&C seminar (May 14th), followed by a proof overview in the student seminar (May 15th)!

010

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 09/05/2025

New paper w/ @felix-zhou-cfz.bsky.social & Alkis Kalavasis! Result: Vanilla SGD (w/ warm start) solves regression with unknown-index self-selection bias Our method speeds up earlier algorithms by Y. Cherapanamjeri, C. Daskalakis, @aifi.bsky.social, M. Zampetakis, J. Gaitonde, & E. Mossel

140

Reposted by @anaymehrotra.bsky.social

Clément Canonne @ccanonne.github.io · 23/04/2025

This looks exciting! arxiv.org/abs/2504.160... by Xi Chen, Shyamal Patel, and Rocco Servedio. An exp(k^1/3)-query adaptive algo for tolerant testing of k-juntas ("is a Boolean function on n variables close from depending on only k variables?"), via a connection to agnostic learning conjunctions.

arxiv.org

A Mysterious Connection Between Tolerant Junta Testing and Agnostically Learning Conjunctions

The main conceptual contribution of this paper is identifying a previously unnoticed connection between two central problems in computational learning theory and property testing: agnostically learnin...

2191

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 22/04/2025

Excellent talk by Jon Kleinberg at the institute for advanced studies on language generation—an exciting new area initiated by Jon and @sendhil.bsky.social, with contributors from many institutions (list below) Link: www.youtube.com/watch?v=zlyr...

youtube.com

Language Generation in the Limit - Jon Kleinberg

YouTube video by Institute for Advanced Study

120

Reposted by @anaymehrotra.bsky.social

Felix Zhou @felix-zhou-cfz.bsky.social · 19/04/2025

"What makes a good fisherman as opposed to other professions?" This question can be formulated as a k-linear regression problem with self-selection bias. Alkis, @anaymehrotra.bsky.social, and I design faster local convergence algorithms for this problem: arxiv.org/abs/2504.07133 (1/7)

arxiv.org

Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases and Beyond

We revisit the problem of estimating $k$ linear regressors with self-selection bias in $d$ dimensions with the maximum selection criterion, as introduced by Cherapanamjeri, Daskalakis, Ilyas, and Zamp...

152

Reposted by @anaymehrotra.bsky.social

Lance Fortnow @lance.fortnow.com · 14/04/2025

STOC Theory Fest in Prague June 23-27. Registration now open. Early deadline is May 6. acm-stoc.org/stoc202... You can apply for student support. Deadline April 27. acm-stoc.org/stoc202...

052

Reposted by @anaymehrotra.bsky.social

Samson Zhou @szhoucs.bsky.social · 04/04/2025

Taking a break from the submission season? Swing by the Workshop on Algorithms for Large Data (Online), WALDO 2025 🗓️ April 14—16: waldo-workshop.github.io/2025.html Registration is free! (but necessary by April 7)

waldo-workshop.github.io

Workshop on Algorithms for Large Data (Online) 2025

034

Reposted by @anaymehrotra.bsky.social

Anupam Gupta @anupamg.bsky.social · 30/11/2024

A reminder about NY Theory Day in a week! Fri Dec 6th! Talks by Amir Abboud, Sanjeev Khanna, Rotem Oshman, and Ron Rothblum! At NYU Tandon! sites.google.com/view/nyctheo... Registration is free, but please register for building access. See you all there!

sites.google.com

Home

About The New York Theory Day is a workshop aimed to bring together the theoretical computer science community in the New York metropolitan area for a day of interaction and discussion. The Theory Da...

1459

anaymehrotra.bsky.social @anaymehrotra.bsky.social · 25/11/2024

We want language models that do not hallucinate We want language models that have breadth (i.e., no mode-collapse) Jon Kleinberg-@sendhil.bsky.social asked: Can we get both? Alkis Kalavasis, Grigoris Velegkas, and I show this is impossible: arxiv.org/abs/2411.09642 🧵(1/3)

Screenshot of a paper with the title "On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse," authored by Alkis Kalavasis (Yale), Anay Mehrotra (Yale), and Grigoris Velegkas (Yale)

130

Reposted by @anaymehrotra.bsky.social

Kira Goldner @kiragoldner.bsky.social · 19/11/2024

I wrote a Part IV postscript to my job market blog post to add what I've learned as faculty. TL;DR: No one is out to get you. For anything not going your way, it's probably due to people being busy or bureaucracy. And there are probably people working very hard for you behind the scenes regardless.

kiragoldner.com

The Job Market (Parts I, II, III, & IV)

0368

Reposted by @anaymehrotra.bsky.social

Rex "garbage in" Douglass @rexdouglass.bsky.social · 23/11/2024

A list of all the stats/modeling/ML/data starter packs I've seen (26+ and counting):

64412

Reposted by @anaymehrotra.bsky.social

Clément Canonne @ccanonne.github.io · 23/11/2024

Optimist: The cup is half full Pessimist: The cup is half empty LaTeX user: The whole spacing and size are wrong, you should have been using \bigcup

3518

Reposted by @anaymehrotra.bsky.social

Clément Canonne @ccanonne.github.io · 23/11/2024

It's tough to gain visibility as a young researcher, and it's job market season! Are you a theoretical computer science PhD/postdoc on the job market? I don't have a crazy juge audience but I'll try to help a bit: fill this form, and I'll tweet your pitch and info! docs.google.com/forms/d/e/1F...

docs.google.com

Theoretical CS Job Market 2024

210538