Optimal scaling of mala for nonlinear regression

被引：18

作者：

Breyer, LA ^{[1
]}

Piccioni, M

Scarlatti, S

机构：

[1] Univ Lancaster, Dept Math & Stat, Fylge Coll, Lancaster LA1 4YF, England

[2] Univ G DAnnunzio, Dipartimento Sci, I-65127 Pescara, Italy

[3] Univ Roma La Sapienza, Dipartimento Matemat, I-00185 Rome, Italy

来源：

ANNALS OF APPLIED PROBABILITY | 2004年 / 14卷 / 03期

关键词：

Bayesian nonlinear regression; Markov chain Monte Carlo; Hastings-Metropolis; Langevin diffusion; propagation of chaos;

D O I：

10.1214/105051604000000369

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

We address the problem of simulating efficiently from the posterior distribution over the parameters of a particular class of nonlinear regression models using a Langevin-Metropolis sampler. It is shown that as the number N of parameters increases, the proposal variance must scale as N-1/3 in order to converge to a diffusion. This generalizes previous results of Roberts and Rosenthal [J. R. Stat. Soc. Ser B Stat. Methodol. 60 (1998) 255-268] for the i.i.d. case, showing the robustness of their analysis.

引用

页码：1479 / 1505

页数：27

共 18 条

[1]

Ben Arous G., 1990, Stoch. Stoch. Rep., V31, P79

[2] From metropolis to diffusions: Gibbs states and optimal scaling [J].

Breyer, LA ;

Roberts, GO .

STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2000, 90 (02) :181-206

[3]

CHRISTENSEN OF, 2003, SCALING LIMITS TRANS

[4] SANOV PROPERTY, GENERALIZED I-PROJECTION AND A CONDITIONAL LIMIT-THEOREM [J].

CSISZAR, I .

ANNALS OF PROBABILITY, 1984, 12 (03) :768-793

[5] I-DIVERGENCE GEOMETRY OF PROBABILITY DISTRIBUTIONS AND MINIMIZATION PROBLEMS [J].

CSISZAR, I .

ANNALS OF PROBABILITY, 1975, 3 (01) :146-158

[6]

Dembo A., 2010, Large Deviations Techniques and Applications

[7]

Ethier S.N., 1986, MARKOV PROCESSES CHA, DOI 10.1002/9780470316658

[8]

Kusuoka S., 1984, Journal of the Faculty of Science, University of Tokyo, Section 1A (Mathematics), V31, P223

[9]

Neal RadfordM., 1996, Priors for Infinite Networks

[10]

PETROV V.V., 1995, Limit Theorems of Probability Theory: Sequences of Independent Random Variables

← 1 2 →