Neural Tangents: Fast and Easy Infinite Neural Networks in Python

TL;DR

Neural Tangents is a Python library that simplifies research on infinite-width neural networks, enabling analytical training and dynamic studies with scalable performance across hardware accelerators.

Contribution

It introduces a high-level API for designing and analyzing infinite neural networks, supporting both finite and infinite-width training methods with efficient distributed computation.

Findings

Supports exact Bayesian inference for infinite networks

Enables analysis of training dynamics of wide finite networks

Runs efficiently on CPU, GPU, and TPU with scalable distribution

Abstract

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 architectures. These networks can then be trained and evaluated either at finite-width as usual or in their infinite-width limit. Infinite-width networks can be trained analytically using exact Bayesian inference or using gradient descent via the Neural Tangent Kernel. Additionally, Neural Tangents provides tools to study gradient descent training dynamics of wide but finite networks in either function space or weight space. The entire library runs out-of-the-box on CPU, GPU, or TPU. All computations can be automatically distributed over multiple accelerators with near-linear scaling in the number of devices. Neural Tangents is available at www.github.com/google/neural-tangents. We also provide an accompanying interactive Colab notebook.