Toggle Poster Visibility
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Grand Ballroom
Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem
[
Oral]
Oral
Thu Jun 13 11:20 AM -- 11:25 AM (PDT) @ Grand Ballroom
On the Spectral Bias of Neural Networks
Oral
Thu Jun 13 11:25 AM -- 11:30 AM (PDT) @ Grand Ballroom
Recursive Sketches for Modular Deep Learning
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Grand Ballroom
Zero-Shot Knowledge Distillation in Deep Networks
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Grand Ballroom
A Convergence Theory for Deep Learning via Over-Parameterization
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Grand Ballroom
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
[
Oral]
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Grand Ballroom
Approximation and non-parametric estimation of ResNet-type convolutional neural networks
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Grand Ballroom
Global Convergence of Block Coordinate Descent in Deep Learning
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Grand Ballroom
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Grand Ballroom
On the Limitations of Representing Functions on Sets