Exciting Update: We've figured out the global convergence rates of BFGS with exact line search! Paper: arxiv.org/pdf/2404.01267…

Excited to receive the Google Research Scholar Award for my work on Learning and Fine-Tuning Large Models in Federated Environments! Google AI research.google/programs-and-e…

🚨 New blog post! Black Box Reductions: Constrained Online Learning From the classic reduction for online learning in the simplex to reductions for arbitrary convex sets, using non-euclidean and Bregman projections Bonus: Simple Regret Matching+ proof parameterfree.com/2024/04/29/bla…

In our ICML Conference "oral" paper, we prove neural networks can learn "nonlinear" representations in multi-task learning settings. Also explain why a more diverse set of tasks improves the learning of these representations. More details: 👇👇

Fantastic news! Congrats to Adam and his collaborators!

Will present this result at STOC this year

Exciting News: I officially got tenure! Huge thanks to my amazing students, collaborators, and mentors!

Excited that our book has found its home at SIAM—big shoutout to my awesome group of co-authors!

Should be a fun workshop!

Also finally decided to dip my toes into academic twitter; hope I’m not too late to the party😅