Archive for mixtures of distributions

the most probable cluster

Posted in Books, Statistics with tags , , , , , , on July 11, 2019 by xi'an

In the last issue of Bayesian Analysis, Lukasz Rajkowski studies the most likely (MAP) cluster associated with the Dirichlet process mixture model. Reminding me that most Bayesian estimates of the number of clusters are not consistent (when the sample size grows to infinity). I am always puzzled by this problem, as estimating the number of clusters sounds like an ill-posed problem, since it is growing with the number of observations, by definition of the Dirichlet process. For instance, the current paper establishes that the number of clusters intersecting a given compact set remains bounded. (The setup is one of a Normal Dirichlet process mixture with constant and known covariance matrix.)

Since the posterior probability of a given partition of {1,2,…,n} can be (formally) computed, the MAP estimate can be (formally) derived. I inserted formally in the previous sentence as the derivation of the exact MAP is an NP hard problem in the number n of observations. As an aside, I have trouble with the author’s argument that the convex hulls of the clusters should be disjoin: I do not see why they should when the mixture components are overlapping. (More generally, I fail to relate to notions like “bad clusters” or “overestimation of the number of clusters” or a “sensible choice” of the covariance matrix.) More globally, I am somewhat perplexed by the purpose of the paper and the relevance of the MAP estimate, even putting aside my generic criticisms of the MAP approach. No uncertainty is attached to the estimator, which thus appears as a form of penalised likelihood strategy rather than a genuinely Bayesian (Analysis) solution.

The first example in the paper is using data from a Uniform over (-1,1), concluding at a “misleading” partition by the MAP since it produces more than one cluster. I find this statement flabbergasting as the generative model is not the estimated model. To wit, the case of an exponential Exp(1) sample that cannot reach a maximum of the target function with a finite number of sample. Which brings me back full-circle to my general unease about clustering in that much more seems to be assumed about this notion than what the statistical model delivers.

O’Bayes 19/1 [snapshots]

Posted in Books, pictures, Statistics, University life with tags , , , , , , , , , , , , , , , , , on June 30, 2019 by xi'an

Although the tutorials of O’Bayes 2019 of yesterday were poorly attended, albeit them being great entries into objective Bayesian model choice, recent advances in MCMC methodology, and the multiple layers of BART, for which I have to blame myself for sticking the beginning of O’Bayes too closely to the end of BNP as only the most dedicated could achieve the commuting from Oxford to Coventry to reach Warwick in time, the first day of talks were well attended, despite weekend commitments, conference fatigue, and perfect summer weather! Here are some snapshots from my bench (and apologies for not covering better the more theoretical talks I had trouble to follow, due to an early and intense morning swimming lesson! Like Steve Walker’s utility based derivation of priors that generalise maximum entropy priors. But being entirely independent from the model does not sound to me like such a desirable feature… And Natalia Bochkina’s Bernstein-von Mises theorem for a location scale semi-parametric model, including a clever construct of a mixture of two Dirichlet priors to achieve proper convergence.)

Jim Berger started the day with a talk on imprecise probabilities, involving the society for imprecise probability, which I discovered while reading Keynes’ book, with a neat resolution of the Jeffreys-Lindley paradox, when re-expressing the null as an imprecise null, with the posterior of the null no longer converging to one, with a limit depending on the prior modelling, if involving a prior on the bias as well, with Chris discussing the talk and mentioning a recent work with Edwin Fong on reinterpreting marginal likelihood as exhaustive X validation, summing over all possible subsets of the data [using log marginal predictive].Håvard Rue did a follow-up talk from his Valencià O’Bayes 2015 talk on PC-priors. With a pretty hilarious introduction on his difficulties with constructing priors and counseling students about their Bayesian modelling. With a list of principles and desiderata to define a reference prior. However, I somewhat disagree with his argument that the Kullback-Leibler distance from the simpler (base) model cannot be scaled, as it is essentially a log-likelihood. And it feels like multivariate parameters need some sort of separability to define distance(s) to the base model since the distance somewhat summarises the whole departure from the simpler model. (Håvard also joined my achievement of putting an ostrich in a slide!) In his discussion, Robin Ryder made a very pragmatic recap on the difficulties with constructing priors. And pointing out a natural link with ABC (which brings us back to Don Rubin’s motivation for introducing the algorithm as a formal thought experiment).

Sara Wade gave the final talk on the day about her work on Bayesian cluster analysis. Which discussion in Bayesian Analysis I alas missed. Cluster estimation, as mentioned frequently on this blog, is a rather frustrating challenge despite the simple formulation of the problem. (And I will not mention Larry’s tequila analogy!) The current approach is based on loss functions directly addressing the clustering aspect, integrating out the parameters. Which produces the interesting notion of neighbourhoods of partitions and hence credible balls in the space of partitions. It still remains unclear to me that cluster estimation is at all achievable, since the partition space explodes with the sample size and hence makes the most probable cluster more and more unlikely in that space. Somewhat paradoxically, the paper concludes that estimating the cluster produces a more reliable estimator on the number of clusters than looking at the marginal distribution on this number. In her discussion, Clara Grazian also pointed the ambivalent use of clustering, where the intended meaning somehow diverges from the meaning induced by the mixture model.

a book and two chapters on mixtures

Posted in Books, Statistics, University life with tags , , , , , , , , , , , , , on January 8, 2019 by xi'an

The Handbook of Mixture Analysis is now out! After a few years of planning, contacts, meetings, discussions about notations, interactions with authors, further interactions with late authors, repeating editing towards homogenisation, and a final professional edit last summer, this collection of nineteen chapters involved thirty-five contributors. I am grateful to all participants to this piece of work, especially to Sylvia Früwirth-Schnatter for being a driving force in the project and for achieving a much higher degree of homogeneity in the book than I expected. I would also like to thank Rob Calver and Lara Spieker of CRC Press for their boundless patience through the many missed deadlines and their overall support.

Two chapters which I co-authored are now available as arXived documents:

5. Gilles Celeux, Kaniav Kamary, Gertraud Malsiner-Walli, Jean-Michel Marin, and Christian P. Robert, Computational Solutions for Bayesian Inference in Mixture Models
7. Gilles Celeux, Sylvia Früwirth-Schnatter, and Christian P. Robert, Model Selection for Mixture Models – Perspectives and Strategies

along other chapters

1. Peter Green, Introduction to Finite Mixtures
8. Bettina Grün, Model-based Clustering
12. Isobel Claire Gormley and Sylvia Früwirth-Schnatter, Mixtures of Experts Models
13. Sylvia Kaufmann, Hidden Markov Models in Time Series, with Applications in Economics
14. Elisabeth Gassiat, Mixtures of Nonparametric Components and Hidden Markov Models
19. Michael A. Kuhn and Eric D. Feigelson, Applications in Astronomy

optimal proposal for ABC

Posted in Statistics with tags , , , , , , , , , , on October 8, 2018 by xi'an

As pointed out by Ewan Cameron in a recent c’Og’ment, Justin Alsing, Benjamin Wandelt, and Stephen Feeney have arXived last August a paper where they discuss an optimal proposal density for ABC-SMC and ABC-PMC. Optimality being understood as maximising the effective sample size.

“Previous studies have sought kernels that are optimal in the (…) Kullback-Leibler divergence between the proposal KDE and the target density.”

The effective sample size for ABC-SMC is actually the regular ESS multiplied by the fraction of accepted simulations. Which surprisingly converges to the ratio

E[q(θ)/π(θ)|D]/E[π(θ)/q(θ)|D]

under the (true) posterior. (Where q(θ) is the importance density and π(θ) the prior density.] When optimised in q, this usually produces an implicit equation which results in a form of geometric mean between posterior and prior. The paper looks at approximate ways to find this optimum. Especially at an upper bound on q. Something I do not understand from the simulations is that the starting point seems to be the plain geometric mean between posterior and prior, in a setting where the posterior is supposedly unavailable… Actually the paper is silent on how the optimal can be approximated in practice, for the very reason I just mentioned. Apart from using a non-parametric or mixture estimate of the posterior after each SMC iteration, which may prove extremely costly when processed through the optimisation steps. However, an interesting if side outcome of these simulations is that the above geometric mean does much better than the posterior itself when considering the effective sample size.

Bayesian gan [gan style]

Posted in Books, pictures, Statistics, University life with tags , , , , , , , , , , , , , on June 26, 2018 by xi'an

In their paper Bayesian GANS, arXived a year ago, Saatchi and Wilson consider a Bayesian version of generative adversarial networks, putting priors on both the model and the discriminator parameters. While the prospect seems somewhat remote from genuine statistical inference, if the following statement is representative

“GANs transform white noise through a deep neural network to generate candidate samples from a data distribution. A discriminator learns, in a supervised manner, how to tune its parameters so as to correctly classify whether a given sample has come from the generator or the true data distribution. Meanwhile, the generator updates its parameters so as to fool the discriminator. As long as the generator has sufficient capacity, it can approximate the cdf inverse-cdf composition required to sample from a data distribution of interest.”

I figure the concept can also apply to a standard statistical model, where x=G(z,θ) rephrases the distributional assumption x~F(x;θ) via a white noise z. This makes resorting to a prior distribution on θ more relevant in the sense of using potential prior information on θ (although the successes of probabilistic numerics show formal priors can be used on purely numerical ground).

The “posterior distribution” that is central to the notion of Bayesian GANs is however unorthodox in that the distribution is associated with the following conditional posteriors

where D(x,θ) is the “discriminator”, that is, in GAN lingo, the probability to be allocated to the “true” data generating mechanism rather than to the one associated with G(·,θ). The generative conditional posterior (1) then aims at fooling the discriminator, i.e. favours generative parameter values that raise the probability of wrong allocation of the pseudo-data. The discriminative conditional posterior (2) is a standard Bayesian posterior based on the original sample and the generated sample. The authors then iteratively sample from these posteriors, effectively implementing a two-stage Gibbs sampler.

“By iteratively sampling from (1) and (2) at every step of an epoch one can, in the limit, obtain samples from the approximate posteriors over [both sets of parameters].”

What worries me about this approach is that  just cannot work, in the sense that (1) and (2) cannot be compatible conditional (posterior) distributions. There is no joint distribution for which (1) and (2) would be the conditionals, since the pseudo-data appears in D for (1) and (1-D) in (2). This means that the convergence of a Gibbs sampler is at best to a stationary σ-finite measure. And hence that the meaning of the chain is delicate to ascertain… Am I missing any fundamental point?! [I checked the reviews on NIPS webpage and could not spot this issue being raised.]

1500 nuances of gan [gan gan style]

Posted in Books, Statistics, University life with tags , , , , , , , , , , , on February 16, 2018 by xi'an

I recently realised that there is a currently very popular trend in machine learning called GAN [for generative adversarial networks] that strongly connects with ABC, at least in that it relies mostly on the availability of a generative model, i.e., a probability model that can be generated as in x=G(ϵ;θ), to draw inference about θ [or predictions]. For instance, there was a GANs tutorial at NIPS 2016 by Ian Goodfellow and many talks on the topic at recent NIPS, the 1500 in the title referring to the citations of the GAN paper by Goodfellow et al. (2014). (The name adversarial comes from opposing true model to generative model in the inference. )

If you remember Jeffreys‘s famous pique about classical tests as being based on improbable events that did not happen, GAN, like ABC,  is sort of the opposite in that it generates events until the one that was observed happens. More precisely, by generating pseudo-samples and switching parameters θ until these samples get as confused as possible between the data generating (“true”) distribution and the generative one. (In its original incarnation, GAN is indeed an optimisation scheme in θ.) A basic presentation of GAN is that it constructs a function D(x,ϕ) that represents the probability that x came from the true model p versus the generative model, ϕ being the parameter of a neural network trained to this effect, aimed at minimising in ϕ a two-term objective function

E[log D(x,ϕ)]+E[log(1D(G(ϵ;θ),ϕ))]

where the first expectation is taken under the true model and the second one under the generative model.

“The discriminator tries to best distinguish samples away from the generator. The generator tries to produce samples that are indistinguishable by the discriminator.” Edward

One ABC perception of this technique is that the confusion rate

E[log(1D(G(ϵ;θ),ϕ))]

is a form of distance between the data and the generative model. Which expectation can be approximated by repeated simulations from this generative model. Which suggests an extension from the optimisation approach to a ABCyesian version by selecting the smallest distances across a range of θ‘s simulated from the prior.

This notion relates to solution using classification tools as density ratio estimation, connecting for instance to Gutmann and Hyvärinen (2012). And ultimately with Geyer’s 1992 normalising constant estimator.

Another link between ABC and networks also came out during that trip. Proposed by Bishop (1994), mixture density networks (MDN) are mixture representations of the posterior [with component parameters functions of the data] trained on the prior predictive through a neural network. These MDNs can be trained on the ABC learning table [based on a specific if redundant choice of summary statistics] and used as substitutes to the posterior distribution, which brings an interesting alternative to Simon Wood’s synthetic likelihood. In a paper I missed Papamakarios and Murray suggest replacing regular ABC with this version…

LaTeX issues from Vienna

Posted in Books, Statistics, University life with tags , , , , , , , , , , , on September 21, 2017 by xi'an

When working on the final stage of our edited handbook on mixtures, in Vienna, I came across unexpected practical difficulties! One was that by working on Dropbox with Windows users, files and directories names suddenly switched from upper case to lower cases letters !, making hard-wired paths to figures and subsections void in the numerous LaTeX files used for the book. And forcing us to change to lower cases everywhere. Having not worked under Windows since George Casella gave me my first laptop in the mid 90’s!, I am amazed that this inability to handle both upper and lower names is still an issue. And that Dropbox replicates it. (And that some people see that as a plus.)

The other LaTeX issue that took a while to solve was that we opted for one chapter one bibliography, rather than having a single bibliography at the end of the book, mainly because CRC Press asked for this feature in order to sell chapters individually… This was my first encounter with this issue and I found the solutions to produce individual bibliographies incredibly heavy handed, whether through chapterbib or bibunits, since one has to bibtex one .aux file for each chapter. Even with a one line bash command,

for f in bu*aux; do bibtex `basename $f .aux`; done

this is annoying in the extreme!