1
|
Doucet A, Moulines E, Thin A. Differentiable samplers for deep latent variable models. Philos Trans A Math Phys Eng Sci 2023; 381:20220147. [PMID: 36970826 PMCID: PMC10041350 DOI: 10.1098/rsta.2022.0147] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Accepted: 02/15/2023] [Indexed: 06/18/2023]
Abstract
Latent variable models are a popular class of models in statistics. Combined with neural networks to improve their expressivity, the resulting deep latent variable models have also found numerous applications in machine learning. A drawback of these models is that their likelihood function is intractable so approximations have to be carried out to perform inference. A standard approach consists of maximizing instead an evidence lower bound (ELBO) obtained based on a variational approximation of the posterior distribution of the latent variables. The standard ELBO can, however, be a very loose bound if the variational family is not rich enough. A generic strategy to tighten such bounds is to rely on an unbiased low-variance Monte Carlo estimate of the evidence. We review here some recent importance sampling, Markov chain Monte Carlo and sequential Monte Carlo strategies that have been proposed to achieve this. This article is part of the theme issue 'Bayesian inference: challenges, perspectives, and prospects'.
Collapse
Affiliation(s)
- Arnaud Doucet
- Department of Statistics, Oxford University, Oxford, UK
| | - Eric Moulines
- Ecole Polytechnique, Centre de Mathématiques Appliquées, CNRS UMR 7641, Palaiseau, France
| | - Achille Thin
- Ecole Polytechnique, Centre de Mathématiques Appliquées, CNRS UMR 7641, Palaiseau, France
| |
Collapse
|
2
|
Cardoso G, Moulines E, Olsson J. Particle-based, Rapid Incremental Smoother Meets Particle Gibbs. Stat Sin 2023. [DOI: 10.5705/ss.202022.0215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/10/2023]
|
3
|
Havet A, Lerasle M, Moulines E, Vernet E. A quantitative McDiarmid’s inequality for geometrically ergodic Markov chains. Electron Commun Probab 2020. [DOI: 10.1214/20-ecp286] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
4
|
|
5
|
Douc R, Fokianos K, Moulines E. Asymptotic properties of quasi-maximum likelihood estimators in observation-driven time series models. Electron J Stat 2017. [DOI: 10.1214/17-ejs1299] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
6
|
Abstract
In this paper, we consider the random-scan symmetric random walk Metropolis algorithm (RSM) onℝd. This algorithm performs a Metropolis step on just one coordinate at a time (as opposed to the full-dimensional symmetric random walk Metropolis algorithm, which proposes a transition on all coordinates at once). We present various sufficient conditions implyingV-uniform ergodicity of the RSM when the target density decreases either subexponentially or exponentially in the tails.
Collapse
|
7
|
Affiliation(s)
- Fredrik Lindsten
- Department of Engineering; The University of Cambridge; Cambridge, CB2 1PZ UK
- Division of Automatic Control; Linköping University; Linköping 58183 Sweden
| | - Randal Douc
- Département CITI; Télécom SudParis; Evry France
| | - Eric Moulines
- Institut Mines-Télécom; Télécom ParisTech; CNRS LTCI, Paris France
| |
Collapse
|
8
|
|
9
|
|
10
|
|
11
|
Kouamo O, Lévy-Leduc C, Moulines E. Central limit theorem for the robust log-regression wavelet estimation of the memory parameter in the Gaussian semi-parametric context. BERNOULLI 2013. [DOI: 10.3150/11-bej398] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
12
|
|
13
|
|
14
|
Abstract
Existing computer simulations of aircraft infrared signature (IRS) do not account for dispersion induced by uncertainty on input data, such as aircraft aspect angles and meteorological conditions. As a result, they are of little use to estimate the detection performance of IR optronic systems; in this case, the scenario encompasses a lot of possible situations that must be indeed addressed, but cannot be singly simulated. In this paper, we focus on low-resolution infrared sensors and we propose a methodological approach for predicting simulated IRS dispersion of poorly known aircraft and performing aircraft detection on the resulting set of low-resolution infrared images. It is based on a sensitivity analysis, which identifies inputs that have negligible influence on the computed IRS and can be set at a constant value, on a quasi-Monte Carlo survey of the code output dispersion, and on a new detection test taking advantage of level sets estimation. This method is illustrated in a typical scenario, i.e., a daylight air-to-ground full-frontal attack by a generic combat aircraft flying at low altitude, over a database of 90,000 simulated aircraft images. Assuming a white noise or a fractional Brownian background model, detection performances are very promising.
Collapse
|
15
|
|
16
|
|
17
|
|
18
|
Cappé O, Moulines E. Corrigendum: On-line expectation-maximization algorithm for latent data models. J R Stat Soc Series B Stat Methodol 2011. [DOI: 10.1111/j.1467-9868.2011.00785.x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
19
|
|
20
|
|
21
|
Lévy-Leduc C, Boistard H, Moulines E, Taqqu MS, Reisen VA. Large sample behaviour of some well-known robust estimators under long-range dependence. STATISTICS-ABINGDON 2011. [DOI: 10.1080/02331888.2011.539442] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
22
|
|
23
|
|
24
|
|
25
|
Douc R, Moulines E, Ritov Y. Forgetting of the initial condition for the filter in general state-space hidden Markov chain: a coupling approach. ELECTRON J PROBAB 2009. [DOI: 10.1214/ejp.v14-593] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
26
|
|
27
|
|
28
|
Douc R, Guillin A, Moulines E. Bounds on regeneration times and limit theorems for subgeometric Markov chains. Ann Inst H Poincaré Probab Statist 2008. [DOI: 10.1214/07-aihp109] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
29
|
Fort G, Meyn S, Moulines E, Priouret P. The ODE method for stability of skip-free Markov chains with applications to MCMC. ANN APPL PROBAB 2008. [DOI: 10.1214/07-aap471] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
30
|
|
31
|
Moulines E, Roueff F, Souloumiac A, Trigano T. Nonparametric inference of photon energy distribution from indirect measurement. BERNOULLI 2007. [DOI: 10.3150/07-bej5184] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
32
|
|
33
|
|
34
|
|
35
|
|
36
|
|
37
|
|
38
|
|
39
|
|
40
|
|
41
|
|
42
|
|