Projected Langevin Monte Carlo algorithms in non-convex and super-linear setting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912208985784320 |
|---|---|
| author | Pang, Chenxu Wang, Xiaojie Wu, Yue |
| author_facet | Pang, Chenxu Wang, Xiaojie Wu, Yue |
| contents | It is of significant interest in many applications to sample from a high-dimensional target distribution $π$ with the density $π(\text{d} x) \propto e^{-U(x)} (\text{d} x) $, based on the temporal discretization of the Langevin stochastic differential equations (SDEs). In this paper, we propose an explicit projected Langevin Monte Carlo (PLMC) algorithm with non-convex potential $U$ and super-linear gradient of $U$ and investigate the non-asymptotic analysis of its sampling error in total variation distance. Equipped with time-independent regularity estimates for the associated Kolmogorov equation, we derive the non-asymptotic bounds on the total variation distance between the target distribution of the Langevin SDEs and the law induced by the PLMC scheme with order $\mathcal{O}(d^{\max\{3γ/2 , 2γ-1 \}} h |\ln h|)$, where $d$ is the dimension of the target distribution and $γ\geq 1$ characterizes the growth of the gradient of $U$. In addition, if the gradient of $U$ is globally Lipschitz continuous, an improved convergence order of $\mathcal{O}(d^{3/2} h)$ for the classical Langevin Monte Carlo (LMC) scheme is derived with a refinement of the proof based on Malliavin calculus techniques. To achieve a given precision $ε$, the smallest number of iterations of the PLMC algorithm is proved to be of order ${\mathcal{O}}\big(\tfrac{d^{\max\{3γ/2 , 2γ-1 \}}}ε \ \cdot \ln (\tfrac{d}ε) \cdot \ln (\tfrac{1}ε) \big)$. In particular, the classical Langevin Monte Carlo (LMC) scheme with the non-convex potential $U$ and the globally Lipschitz gradient of $U$ can be guaranteed by order ${\mathcal{O}}\big(\tfrac{d^{3/2}}ε \cdot \ln (\tfrac{1}ε) \big)$. Numerical experiments are provided to confirm the theoretical findings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_17077 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Projected Langevin Monte Carlo algorithms in non-convex and super-linear setting Pang, Chenxu Wang, Xiaojie Wu, Yue Numerical Analysis Probability 60H35, 65C05, 65C30 It is of significant interest in many applications to sample from a high-dimensional target distribution $π$ with the density $π(\text{d} x) \propto e^{-U(x)} (\text{d} x) $, based on the temporal discretization of the Langevin stochastic differential equations (SDEs). In this paper, we propose an explicit projected Langevin Monte Carlo (PLMC) algorithm with non-convex potential $U$ and super-linear gradient of $U$ and investigate the non-asymptotic analysis of its sampling error in total variation distance. Equipped with time-independent regularity estimates for the associated Kolmogorov equation, we derive the non-asymptotic bounds on the total variation distance between the target distribution of the Langevin SDEs and the law induced by the PLMC scheme with order $\mathcal{O}(d^{\max\{3γ/2 , 2γ-1 \}} h |\ln h|)$, where $d$ is the dimension of the target distribution and $γ\geq 1$ characterizes the growth of the gradient of $U$. In addition, if the gradient of $U$ is globally Lipschitz continuous, an improved convergence order of $\mathcal{O}(d^{3/2} h)$ for the classical Langevin Monte Carlo (LMC) scheme is derived with a refinement of the proof based on Malliavin calculus techniques. To achieve a given precision $ε$, the smallest number of iterations of the PLMC algorithm is proved to be of order ${\mathcal{O}}\big(\tfrac{d^{\max\{3γ/2 , 2γ-1 \}}}ε \ \cdot \ln (\tfrac{d}ε) \cdot \ln (\tfrac{1}ε) \big)$. In particular, the classical Langevin Monte Carlo (LMC) scheme with the non-convex potential $U$ and the globally Lipschitz gradient of $U$ can be guaranteed by order ${\mathcal{O}}\big(\tfrac{d^{3/2}}ε \cdot \ln (\tfrac{1}ε) \big)$. Numerical experiments are provided to confirm the theoretical findings. |
| title | Projected Langevin Monte Carlo algorithms in non-convex and super-linear setting |
| topic | Numerical Analysis Probability 60H35, 65C05, 65C30 |
| url | https://arxiv.org/abs/2312.17077 |