Particle dual averaging: optimization of mean field neural network with global convergence rate analysis* (Q5055425): Difference between revisions

Latest revision as of 15:46, 30 December 2024

scientific article; zbMATH DE number 7632727

Language	Label	Description	Also known as
English	Particle dual averaging: optimization of mean field neural network with global convergence rate analysis*	scientific article; zbMATH DE number 7632727

Statements

instance of

scholarly article

0 references

title

Particle dual averaging: optimization of mean field neural network with global convergence rate analysis* (English)

0 references

0 references

0 references

0 references

Journal of Statistical Mechanics: Theory and Experiment

0 references

publication date

13 December 2022

0 references

full work available at URL

https://arxiv.org/abs/2012.15477

0 references

zbMATH Keywords

deep learning

0 references

machine learning

0 references

stochastic particle dynamics

0 references

describes a project that uses

Scikit

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Gradient descent optimizes over-parameterized deep ReLU networks

0 references

A mean field view of the landscape of two-layer neural networks

0 references

Smooth minimization of non-smooth functions

0 references

Primal-dual subgradient methods for convex problems

0 references

Breaking the Curse of Dimensionality with Convex Neural Networks

0 references

Mean field analysis of neural networks: a central limit theorem

0 references

Q4871571

0 references

The Variational Formulation of the Fokker--Planck Equation

0 references

Q5381127

0 references

Exponential convergence of Langevin distributions and their discrete approximations

0 references

Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.

0 references

Nonasymptotic convergence analysis for the unadjusted Langevin algorithm

0 references

Q4617601

0 references

Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models

0 references

Mixing time guarantees for unadjusted Hamiltonian Monte Carlo

0 references

Logarithmic Sobolev inequalities and stochastic Ising models

0 references

Poincaré and logarithmic Sobolev inequalities by decomposition of the energy landscape

0 references

Couplings and quantitative contraction rates for Langevin dynamics

0 references

Q5396710

0 references

Sample estimate of the entropy of a random vector

0 references

Q5186515

0 references

Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality

0 references

Adaptive estimation of a quadratic functional by model selection.

0 references

Q2855955

0 references

Understanding Machine Learning

0 references

Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler

0 references

Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime

0 references

Mirror descent algorithms for minimizing interacting free energy

0 references

Nonparametric regression using deep neural networks with ReLU activation function

0 references

When do neural networks outperform kernel methods?*

0 references

Identifiers

Mathematics Subject Classification ID

0 references

0 references

0 references

10.1088/1742-5468/AC98A8

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:5055425

@@ Property / DOI @@
-.1088/1742-5468/ac98a8
@@ Property / DOI: 10.1088/1742-5468/ac98a8 / rank @@
-Normal rank
@@ Property / describes a project that uses @@
+Scikit
@@ Property / describes a project that uses: Scikit / rank @@
+Normal rank
@@ Property / MaRDI profile type @@
+MaRDI publication profile
@@ Property / MaRDI profile type: MaRDI publication profile / rank @@
+Normal rank
@@ Property / OpenAlex ID @@
+W3214193129
@@ Property / OpenAlex ID: W3214193129 / rank @@
+Normal rank
@@ Property / cites work @@
+Gradient descent optimizes over-parameterized deep ReLU networks
+Normal rank
@@ Property / cites work @@
+A mean field view of the landscape of two-layer neural networks
+Normal rank
@@ Property / cites work @@
+Smooth minimization of non-smooth functions
@@ Property / cites work: Smooth minimization of non-smooth functions / rank @@
+Normal rank
@@ Property / cites work @@
+Primal-dual subgradient methods for convex problems
+Normal rank
@@ Property / cites work @@
+Breaking the Curse of Dimensionality with Convex Neural Networks
+Normal rank
@@ Property / cites work @@
+Mean field analysis of neural networks: a central limit theorem
+Normal rank
@@ Property / cites work @@
+Q4871571
@@ Property / cites work: Q4871571 / rank @@
+Normal rank
@@ Property / cites work @@
+The Variational Formulation of the Fokker--Planck Equation
+Normal rank
@@ Property / cites work @@
+Q5381127
@@ Property / cites work: Q5381127 / rank @@
+Normal rank
@@ Property / cites work @@
+Exponential convergence of Langevin distributions and their discrete approximations
+Normal rank
@@ Property / cites work @@
+Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
+Normal rank
@@ Property / cites work @@
+Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
+Normal rank
@@ Property / cites work @@
+Q4617601
@@ Property / cites work: Q4617601 / rank @@
+Normal rank
@@ Property / cites work @@
+Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
+Normal rank
@@ Property / cites work @@
+Mixing time guarantees for unadjusted Hamiltonian Monte Carlo
+Normal rank
@@ Property / cites work @@
+Logarithmic Sobolev inequalities and stochastic Ising models
+Normal rank
@@ Property / cites work @@
+Poincaré and logarithmic Sobolev inequalities by decomposition of the energy landscape
+Normal rank
@@ Property / cites work @@
+Couplings and quantitative contraction rates for Langevin dynamics
+Normal rank
@@ Property / cites work @@
+Q5396710
@@ Property / cites work: Q5396710 / rank @@
+Normal rank
@@ Property / cites work @@
+Sample estimate of the entropy of a random vector
@@ Property / cites work: Sample estimate of the entropy of a random vector / rank @@
+Normal rank
@@ Property / cites work @@
+Q5186515
@@ Property / cites work: Q5186515 / rank @@
+Normal rank
@@ Property / cites work @@
+Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
+Normal rank
@@ Property / cites work @@
+Adaptive estimation of a quadratic functional by model selection.
+Normal rank
@@ Property / cites work @@
+Q2855955
@@ Property / cites work: Q2855955 / rank @@
+Normal rank
@@ Property / cites work @@
+Understanding Machine Learning
@@ Property / cites work: Understanding Machine Learning / rank @@
+Normal rank
@@ Property / cites work @@
+Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler
+Normal rank
@@ Property / cites work @@
+Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
+Normal rank
@@ Property / cites work @@
+Mirror descent algorithms for minimizing interacting free energy
+Normal rank
@@ Property / cites work @@
+Nonparametric regression using deep neural networks with ReLU activation function
+Normal rank
@@ Property / cites work @@
+When do neural networks outperform kernel methods?*
+Normal rank
@@ Property / DOI @@
+.1088/1742-5468/AC98A8
@@ Property / DOI: 10.1088/1742-5468/AC98A8 / rank @@
+Normal rank