Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks

• URL: http://arxiv.org/abs/2605.22010v1
• Date: Thu, 21 May 2026 05:14:19 GMT
• Title: Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
• Abstract summary: We find uniform-in-time bounds for $|f__tMF- f_hat_tm|2 lesssim textpoly(d/)$ neurons, training samples, and GD steps.<n>A key takeaway of our result is that whenever the convergence rate of the mean-field, population-loss dynamics is faster than $t-2$, we can attain a loss of $$ with only $textpoly(d/)$ neurons, training samples, and GD steps.
• Score: 37.451796388624864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider one-hidden layer neural networks trained in the feature-learning regime using gradient descent, and relate the output of the finite-width network $f_{\hatρ_t^m}$ to its infinite-width counterpart $f_{ρ_t^{MF}}$, which evolves in the mean-field dynamics. While constant-time horizon bounds for $\|f_{ρ_t^{MF}} - f_{\hatρ_t^m}\|$ may be obtained via standard Grönwall estimates, the long-time behavior of the fluctuation is a more delicate matter. Uniform-in-time bounds often rely on (local) strong convexity in the landscape or Logarithmic Sobolev inequalities present in noisy gradient dynamics. In this work, we establish non-asymptotic weak propagation-of-chaos that holds uniformly in time, obtained by exploiting instead the convergence rate of the mean-field deterministic Wasserstein-gradient-flow dynamics. Specifically, denoting by $L_t$ the mean-field excess MSE loss at time $t$ and $m$ the number of neurons, under standard regularity assumptions and the condition $\int_0^\infty L_t^{1/2} dt =O(\log d)$, we obtain the uniform in time bound $\|f_{ρ_t^{MF}}- f_{\hatρ_t^m}\|^2 \lesssim \text{poly}(d) m^{-\min(1,c/6)}$ whenever $L_t \lesssim t^{-c}$. Our result holds in a noiseless setting and does not make any assumptions on the geometry of the landscape near the optimum, and extends seamlessly to other forms of discretization, including finite number of samples and time discretization. A key takeaway of our result is that whenever the convergence rate of the mean-field, population-loss dynamics is faster than $t^{-2}$, we can attain a loss of $ε$ with only $\text{poly}(d/ε)$ neurons, training samples, and GD steps.

Related papers

• Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise [49.730496294398726]
  We develop a novel quantum mean estimator for heavy-tailed random variables.<n>We derive stronger lower bounds for tail index>4/3$, showing that a nontrivial dependence on a dimension is unavoidable.<n>For a convex objective function, we propose a quantum projected gradient descent method.
  arXiv  Detail & Related papers  (2026-07-28T09:29:37Z)
• Optimal Dimension-Free Sampling for Regularized Classification [56.72526267755301]
  We prove optimal sampling bounds achieving $(1pmvarepsilon)$-relative error for a broad class of Lipschitz continuous classification loss functions.<n>This includes important functions such as logistic and sigmoid loss, hinge loss, and ReLU loss, as prominent and popular representative examples.
  arXiv  Detail & Related papers  (2026-05-22T15:05:33Z)
• Wavelet Variance Equipartition as a Threshold for World-Model Quality and Quantum Kernel TN-Simulability [0.0]
  We identify the wavelet scaling exponent $$ as a critical diagnostic.<n>We establish $= 1/2$ as a sharp transition boundary for the classical simulability of amplitude-encoded quantum kernels.<n>We prove this variance scales strictly as $Var[X] = (d-2)$.
  arXiv  Detail & Related papers  (2026-05-12T05:41:12Z)
• When Does $\ell_2$-Boosting Overfit Benignly? High-Dimensional Risk Asymptotics and the $\ell_1$ Implicit Bias [15.113649527486276]
  We show that benign overfitting fails at the linear rate.<n>We show that while this localization mechanism should persist in the presence of signals, the exact signal-noise decomposition remains an open problem.
  arXiv  Detail & Related papers  (2026-05-07T14:14:09Z)
• Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies [10.511277414974613]
  We study the quantitative convergence of Wasserstein gradient flows of Kernel Mean Discrepancy functionals.<n>Our setting covers in particular the training dynamics of shallow neural networks in the infinite-width and continuous time limit.
  arXiv  Detail & Related papers  (2026-03-02T15:32:54Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise [59.25598762373543]
  We show that wetailed high-prob convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. We demonstrate analytically and that $ta$ can be used to the preferred choice of setting for a given problem.
  arXiv  Detail & Related papers  (2023-10-28T18:53:41Z)
• Projected Langevin dynamics and a gradient flow for entropic optimal transport [0.8057006406834466]
  We introduce analogous diffusion dynamics that sample from an entropy-regularized optimal transport. By studying the induced Wasserstein geometry of the submanifold $Pi(mu,nu)$, we argue that the SDE can be viewed as a Wasserstein gradient flow on this space of couplings.
  arXiv  Detail & Related papers  (2023-09-15T17:55:56Z)
• Generalized moduli of continuity under irregular or random deformations via multiscale analysis [0.0]
  We prove that for signals in multiresolution approximation spaces $U_s$ at scale $s$, stability in $L2$ holds in the regime $|tau|_Linfty/sll 1$.<n>Instability occurs when $|tau|_Linfty/sgg 1$, and we provide a sharp upper bound for the growth rate.
  arXiv  Detail & Related papers  (2021-04-24T16:16:30Z)
• Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization [59.65871549878937]
  We prove that the practical single loop accelerated gradient tracking needs $O(fracgamma1-sigma_gamma)2sqrtfracLepsilon)$.<n>Our convergence rates improve significantly over the ones of $O(frac1epsilon5/7)$ and $O(fracLmu)5/7frac1 (1-sigma)1.5logfrac1epsilon)$.
  arXiv  Detail & Related papers  (2021-04-06T15:34:14Z)
• Agnostic Learning of a Single Neuron with Gradient Descent [92.7662890047311]
  We consider the problem of learning the best-fitting single neuron as measured by the expected square loss. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$.
  arXiv  Detail & Related papers  (2020-05-29T07:20:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.