works on

From the 1 of 1.8k papers with an AI index.

output
20052026
most citedBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

24.4k citations

Showing 2020 · stat.MLShow all

16 papers · 2 filters

stat.ML20206 cited

Graph Networks with Spectral Message Passing

Kimberly Stachenfeld, Jonathan Godwin, Peter Battaglia

Graph Neural Networks (GNNs) are the subject of intense focus by the machine learning community for problems involving relational reasoning. GNNs can be broadly divided into spatia…

stat.ML20201 cited

Integrable Nonparametric Flows

David Pfau, Danilo Rezende

We introduce a method for reconstructing an infinitesimal normalizing flow given only an infinitesimal change to a (possibly unnormalized) probability distribution. This reverses t…

stat.ML202012 cited

Training Generative Adversarial Networks by Solving Ordinary Differential Equations

Chongli Qin, Yan Wu, Jost Tobias Springenberg +4

The instability of Generative Adversarial Network (GAN) training has frequently been attributed to gradient descent. Consequently, recent methods have aimed to tailor the models an…

stat.ML202022 cited

Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition

Ben Adlam, Jeffrey Pennington

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exh…

stat.ML2020

Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein

Khai Nguyen, Son Nguyen, Nhat Ho +2

Relational regularized autoencoder (RAE) is a framework to learn the distribution of data by minimizing a reconstruction loss together with a relational regularization on the laten…

stat.ML202033 cited

The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization

Ben Adlam, Jeffrey Pennington

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastica…