Mallat's one-slide test: are generative models generalizing or just memorizing?

prof_kamilov · x · 2026-09-17

A one-slide idea from Stephane Mallat answers how to tell if a generative model is just memorizing training data: train two models on different sets of faces and give them the same noise.

As the datasets grow, their outputs converge toward each other and drift from individual training examples — evidence of generalization. A simple, intuitive diagnostic.

Original post →

More from Research

Research channel →