Pith. sign in

REVIEW 6 cited by

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

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

arxiv 1902.06720 v4 pith:63VM5QHQ submitted 2019-02-18 stat.ML cs.LG

classification stat.MLcs.LG
keywords networksneuralwidelearninglossagreementdynamicsgaussian
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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 made a theory of learning dynamics elusive. In this work, we show that for wide neural networks the learning dynamics simplify considerably and that, in the infinite width limit, they are governed by a linear model obtained from the first-order Taylor expansion of the network around its initial parameters. Furthermore, mirroring the correspondence between wide Bayesian neural networks and Gaussian processes, gradient-based training of wide neural networks with a squared loss produces test set predictions drawn from a Gaussian process with a particular compositional kernel. While these theoretical results are only exact in the infinite width limit, we nevertheless find excellent empirical agreement between the predictions of the original network and those of the linearized version even for finite practically-sized networks. This agreement is robust across different architectures, optimization methods, and loss functions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product

    math.PR 2026-06 unverdicted novelty 7.0 of 10

    In double asymptotic limits, the squared singular value process of non-square matrix products obeys geometric Dyson Brownian motion whose T-transform solves a Burgers equation, producing the free log-normal law via fr...

  2. Neural Policy Gradient Methods: Global Optimality and Rates of Convergence

    cs.LG 2019-08 conditional novelty 7.0 of 10

    Under strong regularity assumptions, neural natural policy gradient converges to a global optimum at rate O(1/sqrt(T)), and neural vanilla policy gradient converges to a stationary point at the same rate.

  3. Quantitative Understanding of PDF Fits and their Uncertainties

    hep-ph 2025-12 conditional novelty 6.0 of 10

    After an initial transient, a PDF-fitting neural network's output obeys f_t = U(t) f_0 + V(t) Y, a linear blend of the initial network and the data with explicit time-dependent operators.

  4. Pre-Strings Lectures on Artificial Intelligence

    hep-th 2026-07 accept novelty 5.5 of 10

    Lecture notes define neural-network field theory and survey how it recovers known QFT/string results plus applied AI techniques for string problems.

  5. Assessing Quantum Advantage for Gaussian Process Regression

    quant-ph 2025-05 accept novelty 5.0 of 10

    Quantum algorithms for Gaussian process regression lose their exponential speedup because kernel matrix condition numbers grow at least linearly with dataset size.

  6. Finite size corrections for neural network Gaussian processes

    cs.LG 2019-08 conditional novelty 4.0 of 10

    For finite single-hidden-layer networks with symmetric weight initialization, the output distribution is a Gaussian with an O(1/N) fourth-Hermite correction, an instance of the classical Edgeworth expansion.

Pith tools