Archive for Gibbs sampling

more of the same!

Posted in Books, pictures, Statistics, University life with tags , , , , , , , , , on December 10, 2015 by xi'an

aboriginal artist, NGV, Melbourne, July 30, 2012Daniel Seita, Haoyu Chen, and John Canny arXived last week a paper entitled “Fast parallel SAME Gibbs sampling on general discrete Bayesian networks“.  The distributions of the observables are defined by full conditional probability tables on the nodes of a graphical model. The distributions on the latent or missing nodes of the network are multinomial, with Dirichlet priors. To derive the MAP in such models, although this goal is not explicitly stated in the paper till the second page, the authors refer to the recent paper by Zhao et al. (2015), discussed on the ‘Og just as recently, which applies our SAME methodology. Since the paper is mostly computational (and submitted to ICLR 2016, which takes place juuust before AISTATS 2016), I do not have much to comment about it. Except to notice that the authors mention our paper as “Technical report, Statistics and Computing, 2002”. I am not sure the editor of Statistics and Computing will appreciate! The proper reference is in Statistics and Computing, 12:77-84, 2002.

“We argue that SAME is beneficial for Gibbs sampling because it helps to reduce excess variance.”

Still, I am a wee bit surprised at both the above statement and at the comparison with a JAGS implementation. Because SAME augments the number of latent vectors as the number of iterations increases, so should be slower by a mere curse of dimension,, slower than a regular Gibbs with a single latent vector. And because I do not get either the connection with JAGS: SAME could be programmed in JAGS, couldn’t it? If the authors means a regular Gibbs sampler with no latent vector augmentation, the comparison makes little sense as one algorithm aims at the MAP (with a modest five replicas), while the other encompasses the complete posterior distribution. But this sounds unlikely when considering that the larger the number m of replicas the better their alternative to JAGS. It would thus be interesting to understand what the authors mean by JAGS in this setup!

MCMskv, Lenzerheide, 4-7 Jan., 2016 [breaking news #6]

Posted in Kids, Mountains, pictures, Travel, University life with tags , , , , , , , , , , on December 2, 2015 by xi'an

moonriseAs indicated in an earlier MCMskv news, the scientific committee kept a session open for Breaking news! proposals, in conjunction with poster submissions. We received 21 proposals and managed to squeeze 12 fifteen minute presentations in an already tight program. (I advise all participants to take a relaxing New Year break and to load in vitamins and such in preparation for a 24/7 or rather 24/3 relentless and X’citing conference!) Here are the selected presentations, with (some links to my posts on the related papers and) abstracts available on the conference website. Note to all participants that there are still a few days left for submitting posters!

Luke Bornn

Jon Cockayne

Gersende Fort

Michael Gutmann

James Johndrow

Jean-Michel Marin

Murray Pollock

Maxim Rabinovich

Rebecca Steorts

Alexander Terenin

Yazhen Wang

Giacomo Zanella

data augmentation with divergence

Posted in Books, Kids, Statistics, University life with tags , , , , , on November 18, 2015 by xi'an

Another (!) Cross Validated question that shed some light on the difficulties of explaining the convergence of MCMC algorithms. Or in understanding conditioning and hierarchical models. The author wanted to know why a data augmentation of his did not converge: In a simplified setting, given an observation y that he wrote as y=h(x,θ), he had built a Gibbs sampler by reconstructing x=g(y,θ) and simulating θ given x: at each iteration t,

  1. compute xt=g(y,θt-1)
  2. simulate θt~π(θ|xt)

and he attributed the lack of convergence to a possible difficulty with the Jacobian. My own interpretation of the issue was rather that condition on the unobserved x was not the same as conditioning on the observed y and hence that y was missing from step 2. And that the simulation of x is useless. Unless one uses it in an augmented scheme à la Xiao-Li… Nonetheless, I like the problem, if only because my very first reaction was to draw a hierarchical dependence graph and to conclude this should be correct, before checking on a toy example that it was not!

likelihood-free inference in high-dimensional models

Posted in Books, R, Statistics, University life with tags , , , , , , , , , on September 1, 2015 by xi'an

“…for a general linear model (GLM), a single linear function is a sufficient statistic for each associated parameter…”

Water Tower, Michigan Avenue, Chicago, Oct. 31, 2012The recently arXived paper “Likelihood-free inference in high-dimensional models“, by Kousathanas et al. (July 2015), proposes an ABC resolution of the dimensionality curse [when the dimension of the parameter and of the corresponding summary statistics] by turning Gibbs-like and by using a component-by-component ABC-MCMC update that allows for low dimensional statistics. In the (rare) event there exists a conditional sufficient statistic for each component of the parameter vector, the approach is just as justified as when using a generic ABC-Gibbs method based on the whole data. Otherwise, that is, when using a non-sufficient estimator of the corresponding component (as, e.g., in a generalised [not general!] linear model), the approach is less coherent as there is no joint target associated with the Gibbs moves. One may therefore wonder at the convergence properties of the resulting algorithm. The only safe case [in dimension 2] is when one of the restricted conditionals does not depend on the other parameter. Note also that each Gibbs step a priori requires the simulation of a new pseudo-dataset, which may be a major imposition on computing time. And that setting the tolerance for each parameter is a delicate calibration issue because in principle the tolerance should depend on the other component values. Continue reading

Moment conditions and Bayesian nonparametrics

Posted in R, Statistics, University life with tags , , , , , , , , , , on August 6, 2015 by xi'an

Luke Bornn, Neil Shephard, and Reza Solgi (all from Harvard) have arXived a pretty interesting paper on simulating targets on a zero measure set. Although it is not initially presented this way, but rather in non-parametric terms as moment conditions

\mathbb{E}_\theta[g(X,\beta)]=0

where θ is the parameter of the sampling distribution, constrained by the value of β. (Which also contains quantile regression.) The very problem of simulating under a hard constraint has been bugging me for years and it is hence very exciting to see them come up with a proposal towards solving this difficulty! Even though it is restricted here to observations with a finite support (hence allowing for the use of a parametric Dirichlet prior). One interesting extension (Section 3.6) processed in the paper is the case when the support is unknown, but finite, with some points in the support being unobserved. Maybe connecting with non-parametrics if a prior is added on the number of unobserved points.

The setting of constricting θ via a parameterised moment condition relates to moment defined econometrics models, in a similar spirit to Gallant’s paper I recently discussed, but equally to empirical likelihood, which would then benefit from a fully Bayesian treatment thanks to the approach advocated by the authors.

bornnshepardDespite the zero-measure difficulty, or more exactly the non-linear manifold structure of the parameter space, for instance

β = log {θ/(1-θ)}

the authors manage to define a “projected” [my words] measure on the set of admissible pairs (β,θ). In a sense this is related with the choice of a certain metric, but the so-called Hausdorff reference measure allows for an automated definition of the original prior. It took me a (wee) while to spot (p.7) that the starting point was not a (unconstrained) prior on that (unconstrained) pair (β,θ) but directly on the manifold

\mathbb{E}_\theta[g(X,\beta)]=0.

Which makes its construction a difficulty. Even though, as noted in Section 4, all that we need is a prior over θ since the Hausdorff-Jacobian identity defines the “joint”, in a sort of backward way. (This is a wee bit confusing in that β being a transform of θ, all we need is a prior over θ, but we nonetheless end up with a different density on the joint distribution on the pair (β,θ). Any connection with incompatible priors merged together into a consensus prior?) Another question extending the scope of the paper would be to define Jeffreys’ or reference priors in this manifold sense.

The authors also discuss (Section 4.3) the problem I originally thought they were processing, namely starting from an unconstrained pair (β,θ) and it corresponding prior. The projected prior can then be defined based on a version of the original density on the constrained space, but it is definitely arbitrary. In that sense the paper does not address the general problem.

bornnshepard1“…traditional simulation algorithms will fail because the prior and the posterior of the model are supported on a zero Lebesgue measure set…” (p.10)

I somewhat resist this presentation through the measure zero set: once the prior is defined on a manifold, the fact that it is a measure zero set in a larger space is moot. Provided one can simulate a proposal over that manifold, e.g., a random walk, absolutely continuous wrt the same dominating measure, and compute or estimate a Metropolis-Hastings ratio of densities against a common measure, one can formally run MCMC on manifolds as well as regular Euclidean spaces. A first and theoretically straightforward (?) solution is to solve the constraint

\mathbb{E}_\theta[g(X,\beta)]=0

in β=β(θ). Then the joint prior p(β,θ) can be projected by the Hausdorff projection into p(θ). For instance, in the case of the above logit transform, the projected density is

p(θ)=p(β,θ) {1+1/θ²(1-θ)²}½

In practice, the inversion may be too costly and Bornn et al. directly simulate the pair (β,θ) within the manifold capitalising on the fact that the constraint is linear in θ given β. Indeed, in this setting, β is unconstrained and θ can be simulated from a proposal restricted to the hyperplane. Gibbs-like.

Leave the Pima Indians alone!

Posted in Books, R, Statistics, University life with tags , , , , , , , , , , , , , , , , , on July 15, 2015 by xi'an

“…our findings shall lead to us be critical of certain current practices. Specifically, most papers seem content with comparing some new algorithm with Gibbs sampling, on a few small datasets, such as the well-known Pima Indians diabetes dataset (8 covariates). But we shall see that, for such datasets, approaches that are even more basic than Gibbs sampling are actually hard to beat. In other words, datasets considered in the literature may be too toy-like to be used as a relevant benchmark. On the other hand, if ones considers larger datasets (with say 100 covariates), then not so many approaches seem to remain competitive” (p.1)

Nicolas Chopin and James Ridgway (CREST, Paris) completed and arXived a paper they had “threatened” to publish for a while now, namely why using the Pima Indian R logistic or probit regression benchmark for checking a computational algorithm is not such a great idea! Given that I am definitely guilty of such a sin (in papers not reported in the survey), I was quite eager to read the reasons why! Beyond the debate on the worth of such a benchmark, the paper considers a wider perspective as to how Bayesian computation algorithms should be compared, including the murky waters of CPU time versus designer or programmer time. Which plays against most MCMC sampler.

As a first entry, Nicolas and James point out that the MAP can be derived by standard a Newton-Raphson algorithm when the prior is Gaussian, and even when the prior is Cauchy as it seems most datasets allow for Newton-Raphson convergence. As well as the Hessian. We actually took advantage of this property in our comparison of evidence approximations published in the Festschrift for Jim Berger. Where we also noticed the awesome performances of an importance sampler based on the Gaussian or Laplace approximation. The authors call this proposal their gold standard. Because they also find it hard to beat. They also pursue this approximation to its logical (?) end by proposing an evidence approximation based on the above and Chib’s formula. Two close approximations are provided by INLA for posterior marginals and by a Laplace-EM for a Cauchy prior. Unsurprisingly, the expectation-propagation (EP) approach is also implemented. What EP lacks in theoretical backup, it seems to recover in sheer precision (in the examples analysed in the paper). And unsurprisingly as well the paper includes a randomised quasi-Monte Carlo version of the Gaussian importance sampler. (The authors report that “the improvement brought by RQMC varies strongly across datasets” without elaborating for the reasons behind this variability. They also do not report the CPU time of the IS-QMC, maybe identical to the one for the regular importance sampling.) Maybe more surprising is the absence of a nested sampling version.

pimcisIn the Markov chain Monte Carlo solutions, Nicolas and James compare Gibbs, Metropolis-Hastings, Hamiltonian Monte Carlo, and NUTS. Plus a tempering SMC, All of which are outperformed by importance sampling for small enough datasets. But get back to competing grounds for large enough ones, since importance sampling then fails.

“…let’s all refrain from now on from using datasets and models that are too simple to serve as a reasonable benchmark.” (p.25)

This is a very nice survey on the theme of binary data (more than on the comparison of algorithms in that the authors do not really take into account design and complexity, but resort to MSEs versus CPus). I however do not agree with their overall message to leave the Pima Indians alone. Or at least not for the reason provided therein, namely that faster and more accurate approximations methods are available and cannot be beaten. Benchmarks always have the limitation of “what you get is what you see”, i.e., the output associated with a single dataset that only has that many idiosyncrasies. Plus, the closeness to a perfect normal posterior makes the logistic posterior too regular to pause a real challenge (even though MCMC algorithms are as usual slower than iid sampling). But having faster and more precise resolutions should on the opposite be  cause for cheers, as this provides a reference value, a golden standard, to check against. In a sense, for every Monte Carlo method, there is a much better answer, namely the exact value of the integral or of the optimum! And one is hardly aiming at a more precise inference for the benchmark itself: those Pima Indians [whose actual name is Akimel O’odham] with diabetes involved in the original study are definitely beyond help from statisticians and the model is unlikely to carry out to current populations. When the goal is to compare methods, as in our 2009 paper for Jim Berger’s 60th birthday, what matters is relative speed and relative ease of implementation (besides the obvious convergence to the proper target). In that sense bigger and larger is not always relevant. Unless one tackles really big or really large datasets, for which there is neither benchmark method nor reference value.

Overfitting Bayesian mixture models with an unknown number of components

Posted in Statistics with tags , , , , , , , , on March 4, 2015 by xi'an

During my Czech vacations, Zoé van Havre, Nicole White, Judith Rousseau, and Kerrie Mengersen1 posted on arXiv a paper on overfitting mixture models to estimate the number of components. This is directly related with Judith and Kerrie’s 2011 paper and with Zoé’s PhD topic. The paper also returns to the vexing (?) issue of label switching! I very much like the paper and not only because the author are good friends!, but also because it brings a solution to an approach I briefly attempted with Marie-Anne Gruet in the early 1990’s, just before finding about the reversible jump MCMC algorithm of Peter Green at a workshop in Luminy and considering we were not going to “beat the competition”! Hence not publishing the output of our over-fitted Gibbs samplers that were nicely emptying extra components… It also brings a rebuke about a later assertion of mine’s at an ICMS workshop on mixtures, where I defended the notion that over-fitted mixtures could not be detected, a notion that was severely disputed by David McKay…

What is so fantastic in Rousseau and Mengersen (2011) is that a simple constraint on the Dirichlet prior on the mixture weights suffices to guarantee that asymptotically superfluous components will empty out and signal they are truly superfluous! The authors here cumulate the over-fitted mixture with a tempering strategy, which seems somewhat redundant, the number of extra components being a sort of temperature, but eliminates the need for fragile RJMCMC steps. Label switching is obviously even more of an issue with a larger number of components and identifying empty components seems to require a lack of label switching for some components to remain empty!

When reading through the paper, I came upon the condition that only the priors of the weights are allowed to vary between temperatures. Distinguishing the weights from the other parameters does make perfect sense, as some representations of a mixture work without those weights. Still I feel a bit uncertain about the fixed prior constraint, even though I can see the rationale in not allowing for complete freedom in picking those priors. More fundamentally, I am less and less happy with independent identical or exchangeable priors on the components.

Our own recent experience with almost zero weights mixtures (and with Judith, Kaniav, and Kerrie) suggests not using solely a Gibbs sampler there as it shows poor mixing. And even poorer label switching. The current paper does not seem to meet the same difficulties, maybe thanks to (prior) tempering.

The paper proposes a strategy called Zswitch to resolve label switching, which amounts to identify a MAP for each possible number of components and a subsequent relabelling. Even though I do not entirely understand the way the permutation is constructed. I wonder in particular at the cost of the relabelling.

Follow

Get every new post delivered to your Inbox.

Join 981 other followers