Tag: machine learning
All the articles with the tag "machine learning".
-
Stein's paradox
Posted on:In three or more dimensions, the sample mean is dominated everywhere by a shrinkage estimator. The geometric reason is the Gaussian shell: noise pushes you outward, and pulling back is uniformly better. A precursor of ridge regression and most modern regularization.
-
Nearest neighbor breaks in high dimensions
Posted on:In high dimensions, all pairwise distances become essentially equal. Nearest and farthest neighbor are no longer meaningfully different. A short geometric tour of the curse of dimensionality.
-
Optimal message passing on sparse graphs
Posted on:A condensed walkthrough of our NeurIPS 2023 paper deriving the asymptotically Bayes-optimal classifier for node classification on sparse contextual stochastic block models, and what it implies for the design of graph neural networks.
-
Effects of graph convolutions in multi-layer networks
Posted on:A walkthrough of our ICLR 2023 paper on how graph convolutions provably lower the feature-signal threshold for node classification in contextual stochastic block models, and why two convolutions help much more than one.