Deep stable neural networks: large-width asymptotics and convergence rates

DOI10.3150/22-bej1553arXiv2108.02316MaRDI QIDQ6103259

Stefano Favaro, Sandra Fortini, Stefano Peluchetti

Publication date: 2 June 2023

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2108.02316

zbMATH Keywords

spectral measureBayesian inferenceGaussian stochastic processdeep neural networkexchangeable sequencedepth limitneural tangent kernelstable stochastic processinfinitely wide limitsup-norm convergence rate

Mathematics Subject Classification ID

Gaussian processes (60G15) Artificial neural networks and deep learning (68T07) Bayesian inference (62F15) Stable stochastic processes (60G52)

Related Items

-Stable convergence of heavy-/light-tailed infinitely wide neural networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation of multidimensional stable densities
• Bayesian learning for neural networks
• Bayesian neural network priors for edge-preserving inversion
• Metrics for multivariate stable distributions
• Central Limit Theorems for Interchangeable Processes
• Merging of Opinions with Increasing Information
• Inequalities for the $r$th Absolute Moment of a Sum of Random Variables, $1 \leqq r \leqq 2$
• Wide neural networks of any depth evolve as linear models under gradient descent ^*