[ICML 2026] To Grok Grokking: Provable Grokking in Ridge Regression

ACM Transactions on Probabilistic Machine Learning (topml) Vol 2, Issue 2

Unpacking the Grokking Transition: A Deep Dive into Compression Delays in Neural Networks

Exploring how modular arithmetic reveals key insights into neural network embeddings, with compression lagging behind generalization by exte

Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping Saddles

arXiv:2607.09167v1 Announce Type: new Abstract: Schedule-Free methods have attracted growing interest for alleviating the burden of designin

Tiny-diffusion: A minimal implementation of probabilistic diffusion models

Article URL: Comments URL: Points: 4 # Comments: 0

Gaussian Processes for Machine Learning (2006) [pdf]

Article URL: Comments URL: Points: 32 # Comments: 6

Modular: Inkwell: Why Your Inference Platform Matters As Much As Your Model

Inkwell: Why Your Inference Platform Matters As Much As Your Model