Concentration analysis of multivariate elliptic diffusion processes
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914970730496000 |
|---|---|
| author | Aeckerle-Willems, Cathrine Strauch, Claudia Trottner, Lukas |
| author_facet | Aeckerle-Willems, Cathrine Strauch, Claudia Trottner, Lukas |
| contents | We prove concentration inequalities and associated PAC bounds for continuous- and discrete-time additive functionals for possibly unbounded functions of multivariate, nonreversible diffusion processes. Our analysis relies on an approach via the Poisson equation allowing us to consider a very broad class of subexponentially ergodic processes. These results add to existing concentration inequalities for additive functionals of diffusion processes which have so far been only available for either bounded functions or for unbounded functions of processes from a significantly smaller class. We demonstrate the power of these exponential inequalities by two examples of very different areas. Considering a possibly high-dimensional parametric nonlinear drift model under sparsity constraints, we apply the continuous-time concentration results to validate the restricted eigenvalue condition for Lasso estimation, which is fundamental for the derivation of oracle inequalities. The results for discrete additive functionals are used to investigate the unadjusted Langevin MCMC algorithm for sampling of moderately heavy-tailed densities $π$. In particular, we provide PAC bounds for the sample Monte Carlo estimator of integrals $π(f)$ for polynomially growing functions $f$ that quantify sufficient sample and step sizes for approximation within a prescribed margin with high probability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2206_03329 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Concentration analysis of multivariate elliptic diffusion processes Aeckerle-Willems, Cathrine Strauch, Claudia Trottner, Lukas Probability Statistics Theory Machine Learning 60J22, 60J25, 60J60, 62M05, 62H12, 65C05 We prove concentration inequalities and associated PAC bounds for continuous- and discrete-time additive functionals for possibly unbounded functions of multivariate, nonreversible diffusion processes. Our analysis relies on an approach via the Poisson equation allowing us to consider a very broad class of subexponentially ergodic processes. These results add to existing concentration inequalities for additive functionals of diffusion processes which have so far been only available for either bounded functions or for unbounded functions of processes from a significantly smaller class. We demonstrate the power of these exponential inequalities by two examples of very different areas. Considering a possibly high-dimensional parametric nonlinear drift model under sparsity constraints, we apply the continuous-time concentration results to validate the restricted eigenvalue condition for Lasso estimation, which is fundamental for the derivation of oracle inequalities. The results for discrete additive functionals are used to investigate the unadjusted Langevin MCMC algorithm for sampling of moderately heavy-tailed densities $π$. In particular, we provide PAC bounds for the sample Monte Carlo estimator of integrals $π(f)$ for polynomially growing functions $f$ that quantify sufficient sample and step sizes for approximation within a prescribed margin with high probability. |
| title | Concentration analysis of multivariate elliptic diffusion processes |
| topic | Probability Statistics Theory Machine Learning 60J22, 60J25, 60J60, 62M05, 62H12, 65C05 |
| url | https://arxiv.org/abs/2206.03329 |