Happy to share a new blog post w. Xinyi Chen on meta-optimization, and its relationship to adaptive gradient methods and parameter-free optimization! minregret.com/2023/05/15/met…

I will be at NeurIPS - 12th, 13th and will be hanging out at the posters, Sketchy: Vlad Feinberg Xinyi Chen Jennifer Sun Elad Hazan neurips.cc/virtual/2023/p… SoNew: Devvrit Sai Surya Duvvuri Vineet Gupta Cho-Jui Hsieh, Inderjit Dhillon neurips.cc/virtual/2023/p…

See y'all at NeurIPS next week. Presenting Sketchy w Xinyi Chen Jennifer Sun rohan anil Elad Hazan. High level blog post: vladfeinberg.com/2023/10/18/ske… Also, looking for student researchers for OCO🤝Control theory+applied internship! HMU @ NOLA

Excited w. our first research in AI safety & alignment: A game theoretic approach for AI safety via debate: arxiv.org/abs/2312.04792 This is a collaboration with my student Xinyi Chen , our alumna Angelica Chen from NYU, and Dean Foster:

most exciting paper *ever* from our Google AI lab at Princeton University: naman agarwal danielsuo Xinyi Chen arxiv.org/abs/2312.06837 *** Convolutional filters predetermined by the theory, no learning needed! ***

Open source code for spectral SSM is now available! github.com/google-deepmin… Thanks to our Google DeepMind Princeton team: danielsuo naman agarwal Xinyi Chen

New work w/@sadhikamalladi, Lily Zhang@ICML, @xinyichen2, Richard Zhang, Rajesh Ranganath, Kyunghyun Cho: Contrary to conventional wisdom, RLHF/DPO does *not* produce policies that mostly assign higher likelihood to preferred responses than to less preferred ones.

I'll be at ICML Conference next week! Giving a plenary talk at the HiLD workshop and an oral on our recent paper (arxiv.org/abs/2405.19534) at the MHFAIA workshop! Pls reach out to chat if you're also interested in any of these topics! 😊

Want to learn about the math behind robot learning? I'll be presenting an invited talk on "Provable Guarantees for Generative Behavior Cloning" at 11:55am CEST at the 2024 ICML Workshop on Reinforcement Learning at Control (link in 🧵) icml.cc/virtual/2024/w…

Very excited about our work on spectral transformers!

🚨 CMU School of Computer Science PhD applications close tomorrow, December 11, at 3:00pm ET! I’m actively recruiting masters and PhD students interested in the theory and practice of decision making with generative models, especially for robotics, RL and world models! CMU is one of the most

Thank you Max Simchowitz for the shoutout! Making ML more efficient by reasoning about dynamical systems is a really exciting direction, and I look forward to advancing more in this space!

Looking forward to speaking at Princeton SML and next week about neural architectures inspired by dynamical systems: csml.princeton.edu/events/beyond-…