activity
20162026
most citedNeural Tangents: Fast and Easy Infinite Neural Networks in Python

57 citations · 167 across the 14 of their papers we have counts for

collaborators
Showing stat.MLShow all

6 papers · 1 filter

stat.ML2024★ 1 cited

4+3 Phases of Compute-Optimal Neural Scaling Laws

Elliot Paquette, Courtney Paquette, Lechao Xiao +1

We consider the solvable neural scaling model with three parameters: data complexity, target complexity, and model-parameter-count. We use this neural scaling model to derive new p…

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.ML2019★ 57 cited

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

Roman Novak, Lechao Xiao, Jiri Hron +4

Neural Tangents is a library designed to enable research into infinite-width neural networks. It provides a high-level API for specifying complex and hierarchical neural network ar…

stat.ML2019

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

Jaehoon Lee, Lechao Xiao, Samuel S. Schoenholz +4

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have mad…

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…