The mathematics under the hood: optimization methods, convergence guarantees, and the theory that explains when and why deep learning works. Explainers that take proofs seriously without losing the reader.
Ery Arias-Castro and Elizabeth Coda from UC San Diego take an approach inspired by Lebesgue integration — starting from first principles — to show that three intuitive axioms about what a cluster ought to be uniquely recover Hartigan’s cluster tree,…
An Axiomatic Definition of Hierarchical Clustering: Why Hartigan Was Right All Along Read More »
A research team from three leading institutions has proven something nobody expected: when learning a prior across many tasks using the Gibbs algorithm, fast convergence rates are always guaranteed at the meta level — even when individual tasks refuse to…
Bayes Meets Bernstein: Why Meta-Learning Finally Gets Fast — A PAC-Bayes Breakthrough Read More »
A research team from three major U.S. universities has proven for the first time that bilevel optimization algorithms can reliably escape saddle points and find true local minima — solving a problem that has quietly undermined meta-learning, hyperparameter tuning, and…
Tianyi Lin, Chi Jin, and Michael I. Jordan from Columbia, Princeton, and UC Berkeley deliver the first rigorous nonasymptotic analysis of two-timescale gradient descent ascent — the algorithm that has powered GAN training in practice for years — establishing tight…
TTGDA: Two-Timescale Gradient Descent Ascent for Nonconvex Minimax Optimization Read More »
Pierre C. Bellec (Rutgers) and Takuya Koriyama (Chicago Booth) prove that a simple, fully observable formula consistently estimates the prediction error of any Huber-class M-estimator in high dimensions — and that minimizing it over a grid of scale parameters automatically…
Researchers from Michelin and the Centre Borelli at ENS Paris-Saclay have built a smarter way to make neural networks say “I don’t know” — by maximizing the diversity of possible network weights rather than relying on standard regularization that quietly…
Why Your AI Says It’s Confident When It Shouldn’t Be — And How MaxWEnt Fixes It Read More »
Most modern semi supervised learning systems, FixMatch and FreeMatch among the best known, work the same basic way. Take an unlabeled image, run it through the model with a light augmentation, and if the model’s confidence in its own prediction…
Long Tailed Weights Beat Thresholds For Pseudo Labels Read More »