NeurIPS Poster Learnability of high-dimensional targets by two-parameter models and gradient flow

Learnability of high-dimensional targets by two-parameter models and gradient flow

[ Abstract ]

[ Paper] [ Poster] [ OpenReview]

Abstract: We explore the theoretical possibility of learning

d

$d$ -dimensional targets with

W

$W$ -parameter models by gradient flow (GF) when $W

Chat is not available.