🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimal ift.tt/LwFcDjE

Conditional mean embeddings without Tikhonov: no saturation effect! "Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms" #NeurIPS2024 Poster #5709 12 Dec 11 a.m.— 2 p.m neurips.cc/virtual/2024/p… Dimitri Meunier ,Shen,Mattes Mollenhauer , Michael Li

regularization theory fun with Dimitri Meunier at #NeurIPS2024 Thanks for the great collaboration! Arthur Gretton Zikai Shen Michael Li

Happy to see such issues raised and discussed in a NeurIPS workshop. I highly recommend checking the slides at: cims.nyu.edu/~matus/neurips…

Truly excellent piece on entropy. Source: Quanta Magazine search.app/ichMj5mCxENsWC…

Optimal Convergence Rates for Neural Operators ift.tt/JVzpStl

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression ift.tt/8m1M4pd

Characterizing finely the decay of eigenvalues of kernel matrices: many people need it, but explicit references are hard to find. This blog post reviews amazing asymptotic results from Harold Widom (1963!) and proposes new non-asymptotic bounds. francisbach.com/spectrum-kerne…

to provide some substance to the whole reasoning debate

NeurIPS D&B track in a nutshell: (1) An LLM-generated benchmark dataset (2) used to test performance of LLMs (3) evaluated via LLM-as-a-judge

We've written a monograph on Gaussian processes and reproducing kernel methods. arxiv.org/abs/2506.17366

👏 Big shout out to all co-authors for an amazing collab: Patrick Putzky, Pengfei Zhao, Sebastian Schulze, Mattes Mollenhauer, Robert Seidel, Stefan Dietzel, and Thomas Wollmann 📄 Paper: arxiv.org/abs/2502.01717 🧑‍💻 Code: github.com/merantix-momen… 🤗 Models: tinyurl.com/bdacy658

New preprint + code! Neural network compression to any compression rate without re-computation!

You don’t need kindergarten to be a great AI researcher, but I would recommend preschool.