NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#two-layer-networks

0 stories this week · 1 this month · 1 in 6 months · mostly AI

Stories per day · 30 days

Relatedfeature-learning1 learning-dynamics1 statistical-mechanics1 stochastic-gradient-descent1

1 stories, newest first · one card per story

arXiv cs.AI / cs.LG / cs.CL26d ago

Mesoscopic theory describes SGD feature learning in wide two-layer networks

Gaussian overlap statistics track linear and quadratic learning until specialization, which quadratic shielding accelerates.

learning-dynamics two-layer-networks

1