I think it's worth saying something about this when setting expectations for a course. I don't think students should suffer (or athletes), but like, learning is effortful. It should feel challenging. If it doesn't, I'm not helping you. Also we can enjoy effortful things.

Please join #HopkinsDSAI on April 22 for the Johns Hopkins Data Science and AI Institute Spring 2025 Symposium: Human Alignment of AI, featuring speakers including Dr. Tom Griffiths from Princeton University. Event details: ai.jhu.edu/event/spring-2…

Check out Sikata Bela Sengupta and Marcel Hussing, presenting our work Oracle-Efficient RL for Max Value Ensembles at the RL Theory seminar 5/20!

It's Administrative Professionals Day tomorrow, quick, everybody make your admins cookies!

Happy Friday, yall

Congrats to Russell!! 🥳

Come join us! Here's a pic of Locarno, in case that tips the scales for anyone :)

My lab Johns Hopkins University is recruiting research and communications professionals, and AI postdocs to advance our work ensuring that AI is safe and aligned to human well-being worldwide: We're hiring an AI Policy Researcher to conduct in-depth research into the technical and policy

Come hang out and think about crafting and communicating research agendas at COLT 2025!!

For those that couldn't make it, we've uploaded our full STOC workshop on High Dimensional Expanders to Youtube! Hopefully a useful resource for learning the basics of HDX and how they're applied in TCS. Talk 1: An introduction to HDX youtube.com/watch?v=r6mrG3…

Hello from Paris! Let's meet up if you're at COLT next week!

Happening today at 4pm CET in Amphitheater T!

New podcast episode of "Probably Approximately Correct Learners," featuring guest Clément Canonne (Clément Canonne (on Blue🦋Sky))! Check it out on Youtube, Spotify, Apple Podcasts, or wherever you get your podcasts (links in the next post) 1/2

Come say hi at our #ICML poster today during Poster Session 1 (W-600)! Joint work with Aaron Roth Michael Kearns Jess Sorrell Marcel Hussing and Eric Eaton! arxiv.org/abs/2502.11828

Do you care about multiaccuracy/multicalibration in ML? and are you concerned with accessing privileged information (like sensitive attributes) to evaluate or control for these? Then come by Beepul's poster today at #icml where he'll be presenting this work

📢 Attention undergrads! 📢 Check out our 2nd CS Faculty Research Panel of the summer on Thursday, July 31, where faculty like Michael Dinitz, Kimia Ghobadi & Jess Sorrell will help you learn how to apply your degree to the broader world of CS. Learn more at cs.jhu.edu/event/computer…

#HopkinsDSAI welcomes 22 new faculty members, who join more than 150 DSAI faculty members across Johns Hopkins University in advancing the study of data science, machine learning, and #AI and translation to a range of critical and emerging fields. ai.jhu.edu/news/data-scie…

Last call to register at mmlworkshop.ethz.ch for the Math for Trustworthy ML workshop in Switzerland with the possibility to present your own work as poster/talk, we still have a few slots left!

Join Learning Theory Alliance for a mentoring workshop on productive AI use for research and research-adjacent tasks!