Today · 15:00 UTC · Seminarlearning theory
Some Very Old and Very New Problems in Learning Theory
Daniel Barzilai · Weizmann Institute of Science · Online
Two recent theoretical results on the limits of neural-network learning. The first part examines model collapse: what happens to models that are repeatedly retrained on data containing synthetic samples generated by earlier models. The second part asks when and why standard gradient-based learning fails, and presents a framework for proving computational lower bounds for neural networks trained…