ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2001.10423
20
7

Rate of Estimation for the Stationary Distribution of Stochastic Damping Hamiltonian Systems with Continuous Observations

28 January 2020
S. Delattre
A. Gloter
Nakahiro Yoshida
ArXivPDFHTML
Abstract

We study the problem of the non-parametric estimation for the density π\piπ of the stationary distribution of a stochastic two-dimensional damping Hamiltonian system (Zt)t∈[0,T]=(Xt,Yt)t∈[0,T](Z_t)_{t\in[0,T]}=(X_t,Y_t)_{t \in [0,T]}(Zt​)t∈[0,T]​=(Xt​,Yt​)t∈[0,T]​. From the continuous observation of the sampling path on [0,T][0,T][0,T], we study the rate of estimation for π(x0,y0)\pi(x_0,y_0)π(x0​,y0​) as T→∞T \to \inftyT→∞. We show that kernel based estimators can achieve the rate T−vT^{-v}T−v for some explicit exponent v∈(0,1/2)v \in (0,1/2)v∈(0,1/2). One finding is that the rate of estimation depends on the smoothness of π\piπ and is completely different with the rate appearing in the standard i.i.d.\ setting or in the case of two-dimensional non degenerate diffusion processes. Especially, this rate depends also on y0y_0y0​. Moreover, we obtain a minimax lower bound on the L2L^2L2-risk for pointwise estimation, with the same rate T−vT^{-v}T−v, up to log⁡(T)\log(T)log(T) terms.

View on arXiv
Comments on this paper