REVIEW 4 cited by
Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Wide neural networks with random weights and biases are Gaussian processes, as originally observed by Neal (1995) and more recently by Lee et al. (2018) and Matthews et al. (2018) for deep fully-connected networks, as well as by Novak et al. (2019) and Garriga-Alonso et al. (2019) for deep convolutional networks. We show that this Neural Network-Gaussian Process correspondence surprisingly extends to all modern feedforward or recurrent neural networks composed of multilayer perceptron, RNNs (e.g. LSTMs, GRUs), (nD or graph) convolution, pooling, skip connection, attention, batch normalization, and/or layer normalization. More generally, we introduce a language for expressing neural network computations, and our result encompasses all such expressible neural networks. This work serves as a tutorial on the *tensor programs* technique formulated in Yang (2019) and elucidates the Gaussian Process results obtained there. We provide open-source implementations of the Gaussian Process kernels of simple RNN, GRU, transformer, and batchnorm+ReLU network at github.com/thegregyang/GP4A.
Forward citations
Cited by 4 Pith papers
-
The Cost of Discretization in Functional Linear Regression: Minimax Rates and Adaptation
Matching minimax prediction rates for discretely observed functional linear regression are n^{-ν/(ν+1)}+(nm)^{-ν/κ} under independent design, and those two terms plus m^{-ν}+m^{-4α} under common design.
-
On the Stability of the Jacobian Matrix in Deep Neural Networks
A general random matrix stability theorem shows when sparse or correlated neural-network weights still preserve stable Jacobians, and derives the required weight-rescaling.
-
Pre-Strings Lectures on Artificial Intelligence
Lecture notes define neural-network field theory and survey how it recovers known QFT/string results plus applied AI techniques for string problems.
-
Reduced Order Models and Conditional Expectation -- Analysing Parametric Low-Order Approximations
Parametric reduced-order models built by least-squares projection, including POD, reduced basis methods, and Gaussian process emulation, can be viewed as conditional expectations in a Bayesian updating framework.
Discussion (0). Continue with ORCID to comment.