activity
20172022
most citedResurrecting the sigmoid in deep learning through dynamical isometry: theory and practice

69 citations · 304 across the 11 of their papers we have counts for

collaborators
Showing stat.MLShow all

10 papers · 1 filter

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

Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit

Ben Adlam, Jaehoon Lee, Lechao Xiao +2

Modern deep learning models have achieved great success in predictive accuracy for many data modalities. However, their application to many real-world tasks is restricted by poor u…

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…

stat.ML2020

Exact posterior distributions of wide Bayesian neural networks

Jiri Hron, Yasaman Bahri, Roman Novak +2

Recent work has shown that the prior over functions induced by a deep Bayesian neural network (BNN) behaves as a Gaussian process (GP) as the width of all layers becomes large. How…

stat.ML2018

Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes

Roman Novak, Lechao Xiao, Jaehoon Lee +6

There is a previously identified equivalence between wide fully connected neural networks (FCNs) and Gaussian processes (GPs). This equivalence enables, for instance, test set pred…

stat.ML2018

Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks

Lechao Xiao, Yasaman Bahri, Jascha Sohl-Dickstein +2

In recent years, state-of-the-art methods in computer vision have utilized increasingly deep convolutional neural network architectures (CNNs), with some of the most successful mod…