arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.06771math.PRstat.CO
收藏

函数型自回归过程的离散粘性耦合

Discrete sticky couplings of functional autoregressive processes

Alain Durmus, Andreas Eberle, Aurélien Enfroy, Arnaud Guillin, Pierre Monmarché

AI总结:

本文通过构造离散粘性 Markov 链,为函数型自回归过程(包括 Langevin 扩散的 Euler-Maruyama 离散化)建立了关于参数 γ 一致成立的 Wasserstein 和全变差距离非渐近界,并应用于常微分方程参数的贝叶斯推断。

摘要:

本文针对两个具有各向同性高斯噪声的函数型自回归过程,其形式分别为 $Y_{k+1} = \mathrm{T}_γ(Y_k) + \sqrt{γσ^2} Z_{k+1}$ 和 $\tilde{Y}_{k+1} = \tilde{\mathrm{T}}_γ(\tilde{Y}_k) + \sqrt{γσ^2} \tilde{Z}_{k+1}$,给出了它们连续迭代分布之间的 Wasserstein 距离和全变差距离的界。更精确地说,我们给出了关于 $ρ(\mathcal{L}(Y_{k}),\mathcal{L}(\tilde{Y}_k))$ 的非渐近界,其中 $ρ$ 是适当的加权 Wasserstein 距离或 $V$-距离,该界关于参数 $γ$ 一致成立;同时给出了关于 $ρ(π_γ,\tildeπ_γ)$ 的界,其中 $π_γ$ 和 $\tildeπ_γ$ 分别是两个过程的平稳测度。所考虑的过程类涵盖了 Langevin 扩散的 Euler-Maruyama 离散化及其变体。我们推导出的界在 $γ\to 0$ 时具有 $γ$ 的阶。为得到这些结果,我们构造了一个离散粘性 Markov 链 $(W_k^{(γ)})_{k \in \mathbb{N}}$,它界定了两个过程的一个适当耦合之间的距离。随后我们建立了该过程关于 $γ$ 一致成立的稳定性和定量收敛结果。此外,我们证明了它依分布收敛到先前工作中研究的连续粘性过程。最后,我们将结果应用于常微分方程参数的贝叶斯推断,并在两个具体问题上进行了数值说明。

英文摘要:

In this paper, we provide bounds in Wasserstein and total variation distances between the distributions of the successive iterates of two functional autoregressive processes with isotropic Gaussian noise of the form $Y_{k+1} = \mathrm{T}_γ(Y_k) + \sqrt{γσ^2} Z_{k+1}$ and $\tilde{Y}_{k+1} = \tilde{\mathrm{T}}_γ(\tilde{Y}_k) + \sqrt{γσ^2} \tilde{Z}_{k+1}$. More precisely, we give non-asymptotic bounds on $ρ(\mathcal{L}(Y_{k}),\mathcal{L}(\tilde{Y}_k))$, where $ρ$ is an appropriate weighted Wasserstein distance or a $V$-distance, uniformly in the parameter $γ$, and on $ρ(π_γ,\tildeπ_γ)$, where $π_γ$ and $\tildeπ_γ$ are the respective stationary measures of the two processes. The class of considered processes encompasses the Euler-Maruyama discretization of Langevin diffusions and its variants. The bounds we derive are of order $γ$ as $γ\to 0$. To obtain our results, we rely on the construction of a discrete sticky Markov chain $(W_k^{(γ)})_{k \in \mathbb{N}}$ which bounds the distance between an appropriate coupling of the two processes. We then establish stability and quantitative convergence results for this process uniformly on $γ$. In addition, we show that it converges in distribution to the continuous sticky process studied in previous work. Finally, we apply our result to Bayesian inference of ODE parameters and numerically illustrate them on two particular problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑