Conditional path sampling for stochastic differential equations through drift relaxation

DOI10.2140/CAMCOS.2011.6.63MaRDI QIDQ646490zbMATH OpenOpenAlexFDO

Publication date 17 November 2011

Published in Communications in Applied Mathematics and Computational Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1006.2492, http://msp.berkeley.edu/camcos/2011/6-1/p03.xhtml

conditional path sampling homotopy method Monte Carlo particle filter simulated annealing stochastic differential equation

Mathematics Subject Classification ID

Signal detection and filtering (aspects of stochastic processes) (60G35) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Inference from stochastic processes and prediction (62M20) Monte Carlo methods (65C05) Numerical solutions to stochastic differential and integral equations (65C30) Estimation and detection in stochastic control theory (93E10)

Abstract: We present an algorithm for the efficient sampling of conditional paths of stochastic differential equations (SDEs). While unconditional path sampling of SDEs is straightforward, albeit expensive for high dimensional systems of SDEs, conditional path sampling can be difficult even for low dimensional systems. This is because we need to produce sample paths of the SDE which respect both the dynamics of the SDE and the initial and endpoint conditions. The dynamics of a SDE are governed by the deterministic term (drift) and the stochastic term (noise). Instead of producing conditional paths directly from the original SDE, one can consider a sequence of SDEs with modified drifts. The modified drifts should be chosen so that it is easier to produce sample paths which satisfy the initial and endpoint conditions. Also, the sequence of modified drifts converges to the drift of the original SDE. We construct a simple Markov Chain Monte Carlo (MCMC) algorithm which samples, in sequence, conditional paths from the modified SDEs, by taking the last sampled path at each level of the sequence as an initial condition for the sampling at the next level in the sequence. The algorithm can be thought of as a stochastic analog of deterministic homotopy methods for solving nonlinear algebraic equations or as a SDE generalization of simulated annealing. The algorithm is particularly suited for filtering/smoothing applications. We show how it can be used to improve the performance of particle filters. Numerical results for filtering of a stochastic differential equation are included.

Review text

The author presents an algorithm for the efficient sampling of conditional paths of stochastic differential equations (SDEs) \[ dX_t=a(X_t)dt+\sigma(X_t)dB_t, t\in[0,T]. \] To construct sample paths from this equation such that the endpoints are distributed according to the densities \(h(X_0)\) and \(g(X_T)\), respectively, we have to sample the density \[ h(X_{T_0})\prod_{i=1}^{I}p(X_{T_i}|X_{T_{i-1}})g(X_{T_i}), \] where \(0=T_0<T_1<\cdots<T_I=T\) is a partition of the interval \([0,T]\) and \(p(X_{T_i}|X_{T_{i-1}})\) is the transition probability from \(X_{T_{i-1}}\) at time \(T_{i-1}\) to \(X_{T_{i}}\) at time \(T_{i}\) . This density can be sampled using MCMC (Markov Chain Monte Carlo) sampling assuming that the transition densities \(p(X_{T_i}|X_{T_{i-1}})\) can be evaluated. However, the major issue with MCMC sampling is whether it can be performed efficiently. Instead of MCMC sampling directly from the density, the author proposes to provide the MCMC sampler of the density with a better initial condition. He introduces a system of SDEs with modified drift \[ dY_t =b(Y_t)dt + \sigma(Y_t)dB_t, \] where \(b(Y_t)\) is suitably chosen to facilitate the conditional path sampling problem. He considers the collection of \(L+1\) modified systems of SDEs \[ dY^l_t =(1-\epsilon_l)b(Y^l_t)dt +\epsilon_la(Y_t^l)dt+ \sigma(Y^l_t)dB_t, \] where \(0=\epsilon_0<\epsilon_1<\cdots<\epsilon_L=1\). For the \(l\)-th SDE in the sequence, \(p_l(Y^l_{T_i}|Y^l_{T_{i-1}})\) denotes the corresponding transition probability. With this notation \(p_L(Y^L_{T_i}|Y^L_{T_{i-1}})=p(X_{T_i}|X_{T_{i-1}})\). The proposed drift relaxation algorithm is as follows. Sample using MCMC the density \[ h(Y^0_{T_0})\prod_{i=1}^{I}p_0(Y^0_{T_i}|Y^0_{T_{i-1}})g(Y^0_{T_i}). \] For \(l=1,\dots,L\), take the last sample path from the \((l-1)\)-st level and use it as an initial condition for MCMC sampling of the density \[ h(Y^l_{T_0})\prod_{i=1}^{I}p_l(Y^l_{T_i}|Y^l_{T_{i-1}})g(Y^l_{T_i}) \] at the \(l\)-th level. Keep the last sample path at the \(L\)-th level. The levels from 0 to \(L-1\) are auxiliary and only serve the purpose of providing the sampler at level \(L\) with a better initial condition. The final sampling is performed at the \(L\)-th level that corresponds to the original SDE. The drift relaxation algorithm is similar to simulated annealing (SA), used in equilibrium statistical mechanics. The algorithm is particularly suited for filtering/smoothing applications. The author uses the drift relaxation algorithm to modify a popular filtering method called particle filter. The paper contains numerical results of the application of the modified particle filter to the standard example of filtering diffusion in a double-well potential.

Recommendations

Cited in

(10)

This page was built for publication: Conditional path sampling for stochastic differential equations through drift relaxation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q646490)