Stochastic Training is Not Necessary for Generalization

1 code implementation • ICLR 2022 • Jonas Geiping, Micah Goldblum, Phillip E. Pope, Michael Moeller, Tom Goldstein

It is widely believed that the implicit regularization of SGD is fundamental to the impressive generalization behavior we observe in neural networks.

Data Augmentation

Explainability Methods for Graph Convolutional Neural Networks

1 code implementation • CVPR 2019 • Phillip E. Pope, Soheil Kolouri, Mohammad Rostami, Charles E. Martin, Heiko Hoffmann

With the growing use of graph convolutional neural networks (GCNNs) comes the need for explainability.

General Classification

Sliced Wasserstein Auto-Encoders

1 code implementation • ICLR 2019 • Soheil Kolouri, Phillip E. Pope, Charles E. Martin, Gustavo K. Rohde

In this paper we use the geometric properties of the optimal transport (OT) problem and the Wasserstein distances to define a prior distribution for the latent space of an auto-encoder.

Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model

5 code implementations • 5 Apr 2018 • Soheil Kolouri, Phillip E. Pope, Charles E. Martin, Gustavo K. Rohde

In short, we regularize the autoencoder loss with the sliced-Wasserstein distance between the distribution of the encoded training samples and a predefined samplable distribution.