Almanac
paper

How abundant are good interpolators?

paperactiveprovisionalhow-abundant-are-good-interpolators--ac658894·1 events·first seen 12d ago

Aliases: How abundant are good interpolators?

More like this (12)

Recent events (1)

4arXiv · cs.LG·12d ago·source ↗

Large deviation analysis shows most interpolating classifiers share the same generalization performance

A new arXiv preprint establishes a large deviation principle characterizing the generalization performance of interpolating linear classifiers in the overparameterized regime (n/d → α, small α). The key result is a concentration phenomenon: all but an exponentially small fraction of interpolators achieve approximately the same generalization error, determined by a unique rate-function maximizer. Empirically, gradient descent and a natural linear program both outperform this typical interpolator, providing theoretical grounding for benign overfitting in overparameterized models.