2013
DOI: 10.3150/12-bej442
|View full text |Cite
|
Sign up to set email alerts
|

Nonasymptotic bounds on the estimation error of MCMC algorithms

Abstract: We address the problem of upper bounding the mean square error of MCMC estimators. Our analysis is nonasymptotic. We first establish a general result valid for essentially all ergodic Markov chains encountered in Bayesian computation and a possibly unbounded target function $f$. The bound is sharp in the sense that the leading term is exactly $\sigma_{\mathrm {as}}^2(P,f)/n$, where $\sigma_{\mathrm{as}}^2(P,f)$ is the CLT asymptotic variance. Next, we proceed to specific additional assumptions and give explici… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
61
1

Year Published

2014
2014
2016
2016

Publication Types

Select...
5
2

Relationship

2
5

Authors

Journals

citations
Cited by 47 publications
(62 citation statements)
references
References 85 publications
0
61
1
Order By: Relevance
“…For regenerative algorithms, alternative bounds established in [30] are typically tighter than those resulting from our Section 4. However, the algorithms proposed there are more difficult to implement in practically relevant examples.…”
Section: Applicability Of the Resultsmentioning
confidence: 93%
See 2 more Smart Citations
“…For regenerative algorithms, alternative bounds established in [30] are typically tighter than those resulting from our Section 4. However, the algorithms proposed there are more difficult to implement in practically relevant examples.…”
Section: Applicability Of the Resultsmentioning
confidence: 93%
“…Tail inequalities valid in this setup have been established by Bertail and Clémençon in [8] by regenerative approach and using truncation arguments. However, they involve non-explicit constants and cannot be directly applied to derive lower bounds on t and n. In [30] a result analogous to (2) is established for a sequentialregenerative estimator (instead ofÎ t,n (f )). The approach of [30] requires identification of regeneration times.…”
Section: Introductionmentioning
confidence: 97%
See 1 more Smart Citation
“…Indeed, the existing papers [22,23,24,25,26] reported several difficulties to evaluate the variance of the sample mean in the continuous probability space even with the discrete time Markov chain. So, it is remained to extend the obtained results to the continuous case.…”
Section: Resultsmentioning
confidence: 99%
“…PR P-Rank consists of three phases: (a) For pre-processing (lines 1-6), PR P-Rank invokes the randomized algorithm [5] N (u, v) is the sample mean, and σ 2 the variance) , given any accuracy and confidence level 1 − α (α ∈ (0, 1)). This is because applying the Bernstein's Theorem [11] yields exp(− (a) An upper bound can be obtained from Bernstein's Theorem [11], which gives…”
Section: Else If There Exists a Positive Integermentioning
confidence: 99%