On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
From MaRDI portal
Publication:2214233
DOI10.3150/19-BEJ1187zbMath1475.60156arXiv1812.02709OpenAlexW3109128007MaRDI QIDQ2214233
Miklós Rásonyi, Eric Moulines, Ying Zhang, Sotirios Sabanis, M. Barkhagen, N. H. Chau
Publication date: 7 December 2020
Published in: Bernoulli (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1812.02709
Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Diffusion processes (60J60) Applications of Brownian motions and diffusion theory (population genetics, absorption problems, etc.) (60J70)
Related Items
Stochastic gradient Hamiltonian Monte Carlo for non-convex learning, Global Optimization via Schrödinger–Föllmer Diffusion, Functional central limit theorem and strong law of large numbers for stochastic gradient Langevin dynamics, Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization, Convergence of the Kiefer–Wolfowitz algorithm in the presence of discontinuities, Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms, Unnamed Item, On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case, Markov chains in random environment with applications in queuing theory and machine learning, Solving the Kolmogorov PDE by means of deep learning, On the stability of the stochastic gradient Langevin algorithm with dependent data stream, Unadjusted Langevin algorithm for sampling a mixture of weakly smooth potentials
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Existence and stability for Fokker-Planck equations with log-concave reference measure
- Strong approximation of the recursive prediction error estimator of the parameters of an ARMA process
- On Rissanen's predictive stochastic complexity for stationary ARMA processes
- Exponential convergence of Langevin distributions and their discrete approximations
- Introductory lectures on convex optimization. A basic course.
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
- Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
- Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
- A Remark on Stirling's Formula
- A Representation Theorem for the Error of Recursive Estimators
- On the statistical analysis of quantized Gaussian AR(1) processes
- On a class of mixing processes
- AR( infinity ) estimation and nonparametric stochastic complexity
- On fixed gain recursive estimators with discontinuity in the parameters
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- Optimal Transport
