Nov 28, 2022
Speaker · 0 followers
Speaker · 0 followers
We study the dynamics and implicit bias of gradient flow (GF) on univariate ReLU neural networks with a single hidden layer in a binary classification setting. We show that when the labels are determined by the sign of a target network with r neurons, with high probability over the initialization of the network and the sampling of the dataset, GF converges in direction (suitably defined) to a network achieving perfect training accuracy and having at most 𝒪(r) linear regions, implying a generalization bound. Our result may already hold for mild over-parameterization, where the width is 𝒪̃(r) and independent of the sample size.We study the dynamics and implicit bias of gradient flow (GF) on univariate ReLU neural networks with a single hidden layer in a binary classification setting. We show that when the labels are determined by the sign of a target network with r neurons, with high probability over the initialization of the network and the sampling of the dataset, GF converges in direction (suitably defined) to a network achieving perfect training accuracy and having at most 𝒪(r) linear regions, implying a generali…
Account · 954 followers
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Evan Becker, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Dacheng Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Jiaxi Gu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%