Csaba Szepesvari
@CsabaSzepesvari
"If there is not folly in the world, then the world itself is folly. You must understand that mistakes are not always regrets." - Paul Tobin, Bandette🤠
First position paper I ever wrote. "Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence" arxiv.org/abs/2506.23908 Background: I'd like LLMs to help me do math, but statistical learning seems inadequate to make this happen. What do you all think?
So, yea, many implementations you were using are not correct. The beauty of ML and AI. Who cares, does it work?! An important read from my point of view: arxiv.org/pdf/2506.09477… Long live the hacky wacky AI! It works, WHO CARES! Don't forget to make products and to study the…
I hope my Iranian and Israeli friends and their loved ones are safe, and I wish this war ends in a peaceful terminating state soon!
happening soon!
Join us for Nneka's presentation tomorrow! Last talk before the summer break.
RL theory seminars going out with a bang for the summer. make sure to check out @NnekaOkolo4's talk on the best offline RL method for linear MDPs 🔥🔥🔥
Join us for Nneka's presentation tomorrow! Last talk before the summer break.
Happening now! Come join us for a fun chat about randomized (randomised!?) exploration!
Join us tomorrow for Dave's talk! He will present his recent work on randomised exploration, which received an outstanding paper award at ALT 2025 earlier this year.
2024 @TheOfficialACM A.M. Turing Award recipients @RichardSSutton and Andrew G. Barto discuss their #careers and their work on reinforcement learning in an #original #video at bit.ly/43fpe4q
Tomorrow it is time again for a great seminar! Join us to hear out one of Jeongyeol's latest findings.
This is the one that is coming up tomorrow!
should be a great talk by Max, I recommend it!
First seminar of this season is coming up tomorrow! Yay!
Last seminars before the summer break: 04/29: Max Simchowitz (CMU) 05/06: Jeongyeol Kwon (Univ. of Widsconsin-Madison) 05/20: Sikata Sengupta & Marcel Hussing (Univ. of Pennsylvania) 05/27: Dhruv Rohatgi (MIT) 06/03: David Janz (Univ. of Oxford) 06/10: Nneka Okolo (MIT)
Some good stuff coming..
Last seminars before the summer break: 04/29: Max Simchowitz (CMU) 05/06: Jeongyeol Kwon (Univ. of Widsconsin-Madison) 05/20: Sikata Sengupta & Marcel Hussing (Univ. of Pennsylvania) 05/27: Dhruv Rohatgi (MIT) 06/03: David Janz (Univ. of Oxford) 06/10: Nneka Okolo (MIT)
I have had an incredibly positive experience during my sabbatical at Bloomberg. I am glad that they are formalizing this into a program. A major plus for me was that I was treated as fulltime for *everything*. I will be happy to chat in case you had questions about my experience.
We’re excited to announce @Bloomberg's Visiting Faculty Program, a unique chance to collaborate with our researchers on #AI for #finance & tech. Gain access to world-class data & have real-world impact. Apply for sabbaticals & part-time roles: bloom.bg/42yDcOh #research
FYI if you suspect that a reviewer used an LLM to generate an ICML review, you can report them at this link: docs.google.com/forms/d/e/1FAI…
Google link to apply: boards.greenhouse.io/deepmind/jobs/…
Our team at GDM Princeton is hiring! if you want to work on theoretically founded next-gen architectures for LLM, please apply here: sites.google.com/view/gbrainpri…
Last seminar before we take a short break to prepare for the next season! You can send us paper recommendations via this form: forms.gle/Uak8LpVPynNMbf…
Join us tomorrow to attend Vlad's presentation! Related to the seminar from last week, but this time in the offline setting. Tuesday March 25, 6 PM UTC.
There is a postdoctoral position for research on adversarial robustness at UBC, supervised by Mathias Lecuyer (@mathias_lecuyer), Geoff Pleiss, and Nidhi Hegde (@nidhihegde). Please spread the word! 🇨🇦 Link in next tweet 1/2
Another week, another seminar. This time with David ! See you tomorrow at 6 PM UTC