Functional central limit theorem and strong law of large numbers for stochastic gradient Langevin dynamics

DOI10.1007/s00245-023-10052-yarXiv2210.02092OpenAlexW4386223191MaRDI QIDQ6073851

Miklós Rásonyi, Attila Lovas

Publication date: 18 September 2023

Published in: Applied Mathematics and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2210.02092

zbMATH Keywords

functional central limit theoremonline learningmixingstochastic gradient descentMarkov chains in random environments

Mathematics Subject Classification ID

Functional limit theorems; invariance principles (60F17)

Cites Work

• Unnamed Item
• Markov chains and stochastic stability
• A functional central limit theorem for weakly dependent sequences of random variables
• Central limit theorems under weak dependence
• Markov chains in random environment with applications in queuing theory and machine learning
• Invariant measures for multidimensional fractional stochastic volatility models
• On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
• (Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics
• Stochastic approximation with averaging innovation applied to Finance
• On the Averaged Stochastic Approximation for Linear Regression
• On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case