Workshop on Bayesian Inference for Latent Gaussian Models with Applications

  • 1,165 views
Uploaded on

Those are the slides of the invited talk I will give in Zurich on Fed. 05, 2011

Those are the slides of the invited talk I will give in Zurich on Fed. 05, 2011

More in: Technology , Education
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
No Downloads

Views

Total Views
1,165
On Slideshare
0
From Embeds
0
Number of Embeds
1

Actions

Shares
Downloads
25
Comments
0
Likes
1

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide

Transcript

  • 1. ABC Methods for Bayesian Model Choice ABC Methods for Bayesian Model Choice Christian P. Robert Universit´ Paris-Dauphine & CREST e http://www.ceremade.dauphine.fr/~xian February 1, 2011
  • 2. ABC Methods for Bayesian Model Choice Approximate Bayesian computationApproximate Bayesian computation Approximate Bayesian computation ABC basics Alphabet soup Calibration of ABC ABC for model choice
  • 3. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsUntractable likelihoods Cases when the likelihood function f (y|θ) is unavailable and when the completion step f (y|θ) = f (y, z|θ) dz Z is impossible or too costly because of the dimension of z c MCMC cannot be implemented!
  • 4. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsIllustrations Example Stochastic volatility model: for Highest weight trajectories t = 1, . . . , T, 0.4 0.2 yt = exp(zt ) t , zt = a+bzt−1 +σηt , 0.0 −0.2 T very large makes it difficult to −0.4 include z within the simulated 0 200 400 t 600 800 1000 parameters
  • 5. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsIllustrations Example Potts model: if y takes values on a grid Y of size k n and f (y|θ) ∝ exp θ Iyl =yi l∼i where l∼i denotes a neighbourhood relation, n moderately large prohibits the computation of the normalising constant
  • 6. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsIllustrations Example Inference on CMB: in cosmology, study of the Cosmic Microwave Background via likelihoods immensely slow to computate (e.g WMAP, Plank), because of numerically costly spectral transforms [Data is a Fortran program] [Kilbinger et al., 2010, MNRAS]
  • 7. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsIllustrations Example Phylogenetic tree: in population genetics, reconstitution of a common ancestor from a sample of genes via a phylogenetic tree that is close to impossible to integrate out [100 processor days with 4 parameters] [Cornuet et al., 2009, Bioinformatics]
  • 8. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsThe ABC method Bayesian setting: target is π(θ)f (x|θ)
  • 9. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsThe ABC method Bayesian setting: target is π(θ)f (x|θ) When likelihood f (x|θ) not in closed form, likelihood-free rejection technique:
  • 10. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsThe ABC method Bayesian setting: target is π(θ)f (x|θ) When likelihood f (x|θ) not in closed form, likelihood-free rejection technique: ABC algorithm For an observation y ∼ f (y|θ), under the prior π(θ), keep jointly simulating θ ∼ π(θ) , z ∼ f (z|θ ) , until the auxiliary variable z is equal to the observed value, z = y. [Tavar´ et al., 1997] e
  • 11. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsWhy does it work?! The proof is trivial: f (θi ) ∝ π(θi )f (z|θi )Iy (z) z∈D ∝ π(θi )f (y|θi ) = π(θi |y) . [Accept–Reject 101]
  • 12. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsEarlier occurrence ‘Bayesian statistics and Monte Carlo methods are ideally suited to the task of passing many models over one dataset’ [Don Rubin, Annals of Statistics, 1984] Note Rubin (1984) does not promote this algorithm for likelihood-free simulation but frequentist intuition on posterior distributions: parameters from posteriors are more likely to be those that could have generated the data.
  • 13. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsA as approximative When y is a continuous random variable, equality z = y is replaced with a tolerance condition, (y, z) ≤ where is a distance
  • 14. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsA as approximative When y is a continuous random variable, equality z = y is replaced with a tolerance condition, (y, z) ≤ where is a distance Output distributed from π(θ) Pθ { (y, z) < } ∝ π(θ| (y, z) < )
  • 15. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsABC algorithm Algorithm 1 Likelihood-free rejection sampler for i = 1 to N do repeat generate θ from the prior distribution π(·) generate z from the likelihood f (·|θ ) until ρ{η(z), η(y)} ≤ set θi = θ end for where η(y) defines a (maybe in-sufficient) statistic
  • 16. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsOutput The likelihood-free algorithm samples from the marginal in z of: π(θ)f (z|θ)IA ,y (z) π (θ, z|y) = , A ,y ×Θ π(θ)f (z|θ)dzdθ where A ,y = {z ∈ D|ρ(η(z), η(y)) < }.
  • 17. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsOutput The likelihood-free algorithm samples from the marginal in z of: π(θ)f (z|θ)IA ,y (z) π (θ, z|y) = , A ,y ×Θ π(θ)f (z|θ)dzdθ where A ,y = {z ∈ D|ρ(η(z), η(y)) < }. The idea behind ABC is that the summary statistics coupled with a small tolerance should provide a good approximation of the posterior distribution: π (θ|y) = π (θ, z|y)dz ≈ π(θ|y) .
  • 18. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsMA example Consider the MA(q) model q xt = t+ ϑi t−i i=1 Simple prior: uniform prior over the identifiability zone, e.g. triangle for MA(2)
  • 19. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsMA example (2) ABC algorithm thus made of 1. picking a new value (ϑ1 , ϑ2 ) in the triangle 2. generating an iid sequence ( t )−q<t≤T 3. producing a simulated series (xt )1≤t≤T
  • 20. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsMA example (2) ABC algorithm thus made of 1. picking a new value (ϑ1 , ϑ2 ) in the triangle 2. generating an iid sequence ( t )−q<t≤T 3. producing a simulated series (xt )1≤t≤T Distance: basic distance between the series T ρ((xt )1≤t≤T , (xt )1≤t≤T ) = (xt − xt )2 t=1 or distance between summary statistics like the q autocorrelations T τj = xt xt−j t=j+1
  • 21. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsComparison of distance impact Evaluation of the tolerance on the ABC sample against both distances ( = 100%, 10%, 1%, 0.1%) for an MA(2) model
  • 22. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsComparison of distance impact 4 1.5 3 1.0 2 0.5 1 0.0 0 0.0 0.2 0.4 0.6 0.8 −2.0 −1.0 0.0 0.5 1.0 1.5 θ1 θ2 Evaluation of the tolerance on the ABC sample against both distances ( = 100%, 10%, 1%, 0.1%) for an MA(2) model
  • 23. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsComparison of distance impact 4 1.5 3 1.0 2 0.5 1 0.0 0 0.0 0.2 0.4 0.6 0.8 −2.0 −1.0 0.0 0.5 1.0 1.5 θ1 θ2 Evaluation of the tolerance on the ABC sample against both distances ( = 100%, 10%, 1%, 0.1%) for an MA(2) model
  • 24. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsABC advances Simulating from the prior is often poor in efficiency
  • 25. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsABC advances Simulating from the prior is often poor in efficiency Either modify the proposal distribution on θ to increase the density of x’s within the vicinity of y... [Marjoram et al, 2003; Bortot et al., 2007, Sisson et al., 2007]
  • 26. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsABC advances Simulating from the prior is often poor in efficiency Either modify the proposal distribution on θ to increase the density of x’s within the vicinity of y... [Marjoram et al, 2003; Bortot et al., 2007, Sisson et al., 2007] ...or by viewing the problem as a conditional density estimation and by developing techniques to allow for larger [Beaumont et al., 2002]
  • 27. ABC Methods for Bayesian Model Choice Approximate Bayesian computation ABC basicsABC advances Simulating from the prior is often poor in efficiency Either modify the proposal distribution on θ to increase the density of x’s within the vicinity of y... [Marjoram et al, 2003; Bortot et al., 2007, Sisson et al., 2007] ...or by viewing the problem as a conditional density estimation and by developing techniques to allow for larger [Beaumont et al., 2002] .....or even by including in the inferential framework [ABCµ ] [Ratmann et al., 2009]
  • 28. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABC-NP Better usage of [prior] simulations by adjustement: instead of throwing away θ such that ρ(η(z), η(y)) > , replace θs with locally regressed θ∗ = θ − {η(z) − η(y)}T β ˆ [Csill´ry et al., TEE, 2010] e ˆ where β is obtained by [NP] weighted least square regression on (η(z) − η(y)) with weights Kδ {ρ(η(z), η(y))} [Beaumont et al., 2002, Genetics]
  • 29. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABC-MCMC Markov chain (θ(t) ) created via the transition function  θ ∼ Kω (θ |θ(t) ) if x ∼ f (x|θ ) is such that x = y   π(θ )Kω (t) |θ ) θ (t+1) = and u ∼ U(0, 1) ≤ π(θ(t) )K (θ |θ(t) ) ,  ω (θ  (t) θ otherwise,
  • 30. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABC-MCMC Markov chain (θ(t) ) created via the transition function  θ ∼ Kω (θ |θ(t) ) if x ∼ f (x|θ ) is such that x = y   π(θ )Kω (t) |θ ) θ (t+1) = and u ∼ U(0, 1) ≤ π(θ(t) )K (θ |θ(t) ) ,  ω (θ  (t) θ otherwise, has the posterior π(θ|y) as stationary distribution [Marjoram et al, 2003]
  • 31. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABC-MCMC (2) Algorithm 2 Likelihood-free MCMC sampler Use Algorithm 1 to get (θ(0) , z(0) ) for t = 1 to N do Generate θ from Kω ·|θ(t−1) , Generate z from the likelihood f (·|θ ), Generate u from U[0,1] , π(θ )Kω (θ(t−1) |θ ) if u ≤ I π(θ(t−1) Kω (θ |θ(t−1) ) A ,y (z ) then set (θ(t) , z(t) ) = (θ , z ) else (θ(t) , z(t) )) = (θ(t−1) , z(t−1) ), end if end for
  • 32. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupWhy does it work? Acceptance probability that does not involve the calculation of the likelihood and π (θ , z |y) Kω (θ(t−1) |θ )f (z(t−1) |θ(t−1) ) × π (θ(t−1) , z(t−1) |y) Kω (θ |θ(t−1) )f (z |θ ) π(θ ) f (z |θ ) IA ,y (z ) = (t−1) ) f (z(t−1) |θ (t−1) )I (t−1) ) π(θ A ,y (z Kω (θ(t−1) |θ ) f (z(t−1) |θ(t−1) ) × Kω (θ |θ(t−1) ) f (z |θ ) π(θ )Kω (θ(t−1) |θ ) = IA (z ) . π(θ(t−1) Kω (θ |θ(t−1) ) ,y
  • 33. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABCµ [Ratmann, Andrieu, Wiuf and Richardson, 2009, PNAS] Use of a joint density f (θ, |y) ∝ ξ( |y, θ) × πθ (θ) × π ( ) where y is the data, and ξ( |y, θ) is the prior predictive density of ρ(η(z), η(y)) given θ and x when z ∼ f (z|θ)
  • 34. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABCµ [Ratmann, Andrieu, Wiuf and Richardson, 2009, PNAS] Use of a joint density f (θ, |y) ∝ ξ( |y, θ) × πθ (θ) × π ( ) where y is the data, and ξ( |y, θ) is the prior predictive density of ρ(η(z), η(y)) given θ and x when z ∼ f (z|θ) Warning! Replacement of ξ( |y, θ) with a non-parametric kernel approximation.
  • 35. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABCµ details Multidimensional distances ρk (k = 1, . . . , K) and errors k = ρk (ηk (z), ηk (y)), with ˆ 1 k ∼ ξk ( |y, θ) ≈ ξk ( |y, θ) = K[{ k −ρk (ηk (zb ), ηk (y))}/hk ] Bhk b ˆ then used in replacing ξ( |y, θ) with mink ξk ( |y, θ)
  • 36. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABCµ details Multidimensional distances ρk (k = 1, . . . , K) and errors k = ρk (ηk (z), ηk (y)), with ˆ 1 k ∼ ξk ( |y, θ) ≈ ξk ( |y, θ) = K[{ k −ρk (ηk (zb ), ηk (y))}/hk ] Bhk b ˆ then used in replacing ξ( |y, θ) with mink ξk ( |y, θ) ABCµ involves acceptance probability ˆ π(θ , ) q(θ , θ)q( , ) mink ξk ( |y, θ ) ˆ π(θ, ) q(θ, θ )q( , ) mink ξk ( |y, θ)
  • 37. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABCµ multiple errors [ c Ratmann et al., PNAS, 2009]
  • 38. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABCµ for model choice [ c Ratmann et al., PNAS, 2009]
  • 39. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupQuestions about ABCµ For each model under comparison, marginal posterior on used to assess the fit of the model (HPD includes 0 or not).
  • 40. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupQuestions about ABCµ For each model under comparison, marginal posterior on used to assess the fit of the model (HPD includes 0 or not). Is the data informative about ? [Identifiability] How is the prior π( ) impacting the comparison? How is using both ξ( |x0 , θ) and π ( ) compatible with a standard probability model? [remindful of Wilkinson] Where is the penalisation for complexity in the model comparison? [X, Mengersen & Chen, 2010, PNAS]
  • 41. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupA PMC version Use of the same kernel idea as ABC-PRC but with IS correction Generate a sample at iteration t by N (t) (t−1) (t−1) πt (θ ) ∝ ˆ ωj Kt (θ(t) |θj ) j=1 modulo acceptance of the associated xt , and use an importance (t) weight associated with an accepted simulation θi (t) (t) (t) ωi ∝ π(θi ) πt (θi ) . ˆ c Still likelihood free [Beaumont et al., 2008, arXiv:0805.2256]
  • 42. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupSequential Monte Carlo SMC is a simulation technique to approximate a sequence of related probability distributions πn with π0 “easy” and πT as target. Iterated IS as PMC : particles moved from time n to time n via kernel Kn and use of a sequence of extended targets πn˜ n πn (z0:n ) = πn (zn ) ˜ Lj (zj+1 , zj ) j=0 where the Lj ’s are backward Markov kernels [check that πn (zn ) is a marginal] [Del Moral, Doucet & Jasra, Series B, 2006]
  • 43. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupABC-SMC True derivation of an SMC-ABC algorithm Use of a kernel Kn associated with target π n and derivation of the backward kernel π n (z )Kn (z , z) Ln−1 (z, z ) = πn (z) Update of the weights M m=1 IA n (xm ) in win ∝ wi(n−1) M m=1 IA n−1 (xm i(n−1) ) when xm ∼ K(xi(n−1) , ·) in
  • 44. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupProperties of ABC-SMC The ABC-SMC method properly uses a backward kernel L(z, z ) to simplify the importance weight and to remove the dependence on the unknown likelihood from this weight. Update of importance weights is reduced to the ratio of the proportions of surviving particles Major assumption: the forward kernel K is supposed to be invariant against the true target [tempered version of the true posterior]
  • 45. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupProperties of ABC-SMC The ABC-SMC method properly uses a backward kernel L(z, z ) to simplify the importance weight and to remove the dependence on the unknown likelihood from this weight. Update of importance weights is reduced to the ratio of the proportions of surviving particles Major assumption: the forward kernel K is supposed to be invariant against the true target [tempered version of the true posterior] Adaptivity in ABC-SMC algorithm only found in on-line construction of the thresholds t , slowly enough to keep a large number of accepted transitions [Del Moral, Doucet & Jasra, 2009]
  • 46. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupSummary statistics Optimality of the posterior expectations of the parameters of interest as summary statistics!
  • 47. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Alphabet soupSummary statistics Optimality of the posterior expectations of the parameters of interest as summary statistics! Use of the standard quadratic loss function (θ − θ0 )T A(θ − θ0 ) .
  • 48. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Calibration of ABCWhich summary? Fundamental difficulty of the choice of the summary statistic when there is no non-trivial sufficient statistics [except when done by the experimenters in the field]
  • 49. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Calibration of ABCWhich summary? Fundamental difficulty of the choice of the summary statistic when there is no non-trivial sufficient statistics [except when done by the experimenters in the field] Starting from a large collection of summary statistics is available, Joyce and Marjoram (2008) consider the sequential inclusion into the ABC target, with a stopping rule based on a likelihood ratio test.
  • 50. ABC Methods for Bayesian Model Choice Approximate Bayesian computation Calibration of ABCWhich summary? Fundamental difficulty of the choice of the summary statistic when there is no non-trivial sufficient statistics [except when done by the experimenters in the field] Starting from a large collection of summary statistics is available, Joyce and Marjoram (2008) consider the sequential inclusion into the ABC target, with a stopping rule based on a likelihood ratio test. Does not taking into account the sequential nature of the tests Depends on parameterisation Order of inclusion matters.
  • 51. ABC Methods for Bayesian Model Choice ABC for model choiceABC for model choice Approximate Bayesian computation ABC for model choice Model choice Gibbs random fields Generic ABC model choice
  • 52. ABC Methods for Bayesian Model Choice ABC for model choice Model choiceBayesian model choice Several models M1 , M2 , . . . are considered simultaneously for a dataset y and the model index M is part of the inference. Use of a prior distribution. π(M = m), plus a prior distribution on the parameter conditional on the value m of the model index, πm (θ m ) Goal is to derive the posterior distribution of M , challenging computational target when models are complex.
  • 53. ABC Methods for Bayesian Model Choice ABC for model choice Model choiceGeneric ABC for model choice Algorithm 3 Likelihood-free model choice sampler (ABC-MC) for t = 1 to T do repeat Generate m from the prior π(M = m) Generate θ m from the prior πm (θ m ) Generate z from the model fm (z|θ m ) until ρ{η(z), η(y)} < Set m(t) = m and θ (t) = θ m end for [Toni, Welch, Strelkowa, Ipsen & Stumpf, 2009]
  • 54. ABC Methods for Bayesian Model Choice ABC for model choice Model choiceABC estimates Posterior probability π(M = m|y) approximated by the frequency of acceptances from model m T 1 Im(t) =m . T t=1 Early issues with implementation: should tolerances be the same for all models? should summary statistics vary across models? should the distance measure ρ vary as well?
  • 55. ABC Methods for Bayesian Model Choice ABC for model choice Model choiceABC estimates Posterior probability π(M = m|y) approximated by the frequency of acceptances from model m T 1 Im(t) =m . T t=1 Early issues with implementation: should tolerances be the same for all models? should summary statistics vary across models? should the distance measure ρ vary as well? Extension to a weighted polychotomous logistic regression estimate of π(M = m|y), with non-parametric kernel weights [Cornuet et al., DIYABC, 2009]
  • 56. ABC Methods for Bayesian Model Choice ABC for model choice Model choiceThe Great ABC controversy [# 1?] On-going controvery in phylogeographic genetics about the validity of using ABC for testing Against: Templeton, 2008, 2009, 2010a, 2010b, 2010c argues that nested hypotheses cannot have higher probabilities than nesting hypotheses (!)
  • 57. ABC Methods for Bayesian Model Choice ABC for model choice Model choiceThe Great ABC controversy [# 1?] On-going controvery in phylogeographic genetics about the validity of using ABC for testing Replies: Fagundes et al., 2008, Against: Templeton, 2008, Beaumont et al., 2010, Berger et 2009, 2010a, 2010b, 2010c al., 2010, Csill`ry et al., 2010 e argues that nested hypotheses point out that the criticisms are cannot have higher probabilities addressed at [Bayesian] than nesting hypotheses (!) model-based inference and have nothing to do with ABC...
  • 58. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsGibbs random fields Gibbs distribution The rv y = (y1 , . . . , yn ) is a Gibbs random field associated with the graph G if 1 f (y) = exp − Vc (yc ) , Z c∈C where Z is the normalising constant, C is the set of cliques of G and Vc is any function also called potential U (y) = c∈C Vc (yc ) is the energy function
  • 59. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsGibbs random fields Gibbs distribution The rv y = (y1 , . . . , yn ) is a Gibbs random field associated with the graph G if 1 f (y) = exp − Vc (yc ) , Z c∈C where Z is the normalising constant, C is the set of cliques of G and Vc is any function also called potential U (y) = c∈C Vc (yc ) is the energy function c Z is usually unavailable in closed form
  • 60. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsPotts model Potts model Vc (y) is of the form Vc (y) = θS(y) = θ δyl =yi l∼i where l∼i denotes a neighbourhood structure
  • 61. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsPotts model Potts model Vc (y) is of the form Vc (y) = θS(y) = θ δyl =yi l∼i where l∼i denotes a neighbourhood structure In most realistic settings, summation Zθ = exp{θ T S(x)} x∈X involves too many terms to be manageable and numerical approximations cannot always be trusted
  • 62. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsBayesian Model Choice Comparing a model with energy S0 taking values in Rp0 versus a model with energy S1 taking values in Rp1 can be done through the Bayes factor corresponding to the priors π0 and π1 on each parameter space exp{θ T S0 (x)}/Zθ 0 ,0 π0 (dθ 0 ) 0 Bm0 /m1 (x) = exp{θ T S1 (x)}/Zθ 1 ,1 π1 (dθ 1 ) 1
  • 63. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsNeighbourhood relations Choice to be made between M neighbourhood relations m i∼i (0 ≤ m ≤ M − 1) with Sm (x) = I{xi =xi } m i∼i driven by the posterior probabilities of the models.
  • 64. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsModel index Computational target: P(M = m|x) ∝ fm (x|θm )πm (θm ) dθm π(M = m) , Θm
  • 65. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsModel index Computational target: P(M = m|x) ∝ fm (x|θm )πm (θm ) dθm π(M = m) , Θm If S(x) sufficient statistic for the joint parameters (M, θ0 , . . . , θM −1 ), P(M = m|x) = P(M = m|S(x)) .
  • 66. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsSufficient statistics in Gibbs random fields
  • 67. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsSufficient statistics in Gibbs random fields Each model m has its own sufficient statistic Sm (·) and S(·) = (S0 (·), . . . , SM −1 (·)) is also (model-)sufficient.
  • 68. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsSufficient statistics in Gibbs random fields Each model m has its own sufficient statistic Sm (·) and S(·) = (S0 (·), . . . , SM −1 (·)) is also (model-)sufficient. For Gibbs random fields, 1 2 x|M = m ∼ fm (x|θm ) = fm (x|S(x))fm (S(x)|θm ) 1 = f 2 (S(x)|θm ) n(S(x)) m where n(S(x)) = {˜ ∈ X : S(˜ ) = S(x)} x x c S(x) is therefore also sufficient for the joint parameters
  • 69. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsABC model choice Algorithm ABC-MC Generate m∗ from the prior π(M = m). ∗ Generate θm∗ from the prior πm∗ (·). Generate x∗ from the model fm∗ (·|θm∗ ). ∗ Compute the distance ρ(S(x0 ), S(x∗ )). Accept (θm∗ , m∗ ) if ρ(S(x0 ), S(x∗ )) < . ∗ Note When = 0 the algorithm is exact
  • 70. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsToy example iid Bernoulli model versus two-state first-order Markov chain, i.e. n f0 (x|θ0 ) = exp θ0 I{xi =1} {1 + exp(θ0 )}n , i=1 versus n 1 f1 (x|θ1 ) = exp θ1 I{xi =xi−1 } {1 + exp(θ1 )}n−1 , 2 i=2 with priors θ0 ∼ U(−5, 5) and θ1 ∼ U(0, 6) (inspired by “phase transition” boundaries).
  • 71. ABC Methods for Bayesian Model Choice ABC for model choice Gibbs random fieldsToy example (2) 10 5 5 BF01 BF01 0 ^ ^ 0 −5 −5 −40 −20 0 10 −10 −40 −20 0 10 BF01 BF01 (left) Comparison of the true BF m0 /m1 (x0 ) with BF m0 /m1 (x0 ) (in logs) over 2, 000 simulations and 4.106 proposals from the prior. (right) Same when using tolerance corresponding to the 1% quantile on the distances.
  • 72. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceBack to sufficiency ‘Sufficient statistics for individual models are unlikely to be very informative for the model probability. This is already well known and understood by the ABC-user community.’ [Scott Sisson, Jan. 31, 2011, ’Og]
  • 73. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceBack to sufficiency ‘Sufficient statistics for individual models are unlikely to be very informative for the model probability. This is already well known and understood by the ABC-user community.’ [Scott Sisson, Jan. 31, 2011, ’Og] If η1 (x) sufficient statistic for model m = 1 and parameter θ1 and η2 (x) sufficient statistic for model m = 2 and parameter θ2 , (η1 (x), η2 (x)) is not always sufficient for (m, θm )
  • 74. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceBack to sufficiency ‘Sufficient statistics for individual models are unlikely to be very informative for the model probability. This is already well known and understood by the ABC-user community.’ [Scott Sisson, Jan. 31, 2011, ’Og] If η1 (x) sufficient statistic for model m = 1 and parameter θ1 and η2 (x) sufficient statistic for model m = 2 and parameter θ2 , (η1 (x), η2 (x)) is not always sufficient for (m, θm ) c Potential loss of information at the testing level
  • 75. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceLimiting behaviour of B12 (T → ∞) ABC approximation T t=1 Imt =1 Iρ{η(zt ),η(y)}≤ B12 (y) = T , t=1 Imt =2 Iρ{η(zt ),η(y)}≤ where the (mt , z t )’s are simulated from the (joint) prior
  • 76. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceLimiting behaviour of B12 (T → ∞) ABC approximation T t=1 Imt =1 Iρ{η(zt ),η(y)}≤ B12 (y) = T , t=1 Imt =2 Iρ{η(zt ),η(y)}≤ where the (mt , z t )’s are simulated from the (joint) prior As T go to infinity, limit Iρ{η(z),η(y)}≤ π1 (θ 1 )f1 (z|θ 1 ) dz dθ 1 B12 (y) = Iρ{η(z),η(y)}≤ π2 (θ 2 )f2 (z|θ 2 ) dz dθ 2 η Iρ{η,η(y)}≤ π1 (θ 1 )f1 (η|θ 1 ) dη dθ 1 = η , Iρ{η,η(y)}≤ π2 (θ 2 )f2 (η|θ 2 ) dη dθ 2 η η where f1 (η|θ 1 ) and f2 (η|θ 2 ) distributions of η(z)
  • 77. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceLimiting behaviour of B12 ( → 0) When goes to zero, η η π1 (θ 1 )f1 (η(y)|θ 1 ) dθ 1 B12 (y) = η , π2 (θ 2 )f2 (η(y)|θ 2 ) dθ 2
  • 78. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceLimiting behaviour of B12 ( → 0) When goes to zero, η η π1 (θ 1 )f1 (η(y)|θ 1 ) dθ 1 B12 (y) = η , π2 (θ 2 )f2 (η(y)|θ 2 ) dθ 2 Bayes factor based on the sole observation of η(y)
  • 79. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceLimiting behaviour of B12 (under sufficiency) If η(y) sufficient statistic for both models, fi (y|θ i ) = gi (y)fiη (η(y)|θ i ) Thus η Θ1 π(θ 1 )g1 (y)f1 (η(y)|θ 1 ) dθ 1 B12 (y) = η Θ2 π(θ 2 )g2 (y)f2 (η(y)|θ 2 ) dθ 2 η g1 (y) π1 (θ 1 )f1 (η(y)|θ 1 ) dθ 1 = η g2 (y) π2 (θ 2 )f2 (η(y)|θ 2 ) dθ 2 g1 (y) η = B (y) . g2 (y) 12
  • 80. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceLimiting behaviour of B12 (under sufficiency) If η(y) sufficient statistic for both models, fi (y|θ i ) = gi (y)fiη (η(y)|θ i ) Thus η Θ1 π(θ 1 )g1 (y)f1 (η(y)|θ 1 ) dθ 1 B12 (y) = η Θ2 π(θ 2 )g2 (y)f2 (η(y)|θ 2 ) dθ 2 η g1 (y) π1 (θ 1 )f1 (η(y)|θ 1 ) dθ 1 = η g2 (y) π2 (θ 2 )f2 (η(y)|θ 2 ) dθ 2 g1 (y) η = B (y) . g2 (y) 12 No discrepancy only when cross-model sufficiency
  • 81. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choicePoisson/geometric example Sample x = (x1 , . . . , xn ) from either a Poisson P(λ) or from a geometric G(p) Sum n S= yi = η(x) i=1 sufficient statistic for either model but not simultaneously Discrepancy ratio g1 (x) S!n−S / i yi ! = g2 (x) 1 n+S−1 S
  • 82. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choicePoisson/geometric discrepancy η Range of B12 (x) versus B12 (x) B12 (x): The values produced have nothing in common.
  • 83. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceFormal recovery Creating an encompassing exponential family T T f (x|θ1 , θ2 , α1 , α2 ) ∝ exp{θ1 η1 (x) + θ1 η1 (x) + α1 t1 (x) + α2 t2 (x)} leads to a sufficient statistic (η1 (x), η2 (x), t1 (x), t2 (x)) [Didelot, Everitt, Johansen & Lawson, 2011]
  • 84. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceFormal recovery Creating an encompassing exponential family T T f (x|θ1 , θ2 , α1 , α2 ) ∝ exp{θ1 η1 (x) + θ1 η1 (x) + α1 t1 (x) + α2 t2 (x)} leads to a sufficient statistic (η1 (x), η2 (x), t1 (x), t2 (x)) [Didelot, Everitt, Johansen & Lawson, 2011] In the Poisson/geometric case, if i xi ! is added to S,
  • 85. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceFormal recovery Creating an encompassing exponential family T T f (x|θ1 , θ2 , α1 , α2 ) ∝ exp{θ1 η1 (x) + θ1 η1 (x) + α1 t1 (x) + α2 t2 (x)} leads to a sufficient statistic (η1 (x), η2 (x), t1 (x), t2 (x)) [Didelot, Everitt, Johansen & Lawson, 2011] Only applies in genuine sufficiency settings... c Inability to evaluate loss brought by summary statistics
  • 86. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceMeaning of the ABC-Bayes factor ‘This is also why focus on model discrimination typically (...) proceeds by (...) accepting that the Bayes Factor that one obtains is only derived from the summary statistics and may in no way correspond to that of the full model.’ [Scott Sisson, Jan. 31, 2011, ’Og]
  • 87. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceMeaning of the ABC-Bayes factor ‘This is also why focus on model discrimination typically (...) proceeds by (...) accepting that the Bayes Factor that one obtains is only derived from the summary statistics and may in no way correspond to that of the full model.’ [Scott Sisson, Jan. 31, 2011, ’Og] In the Poisson/geometric case, if E[yi ] = θ0 > 0, η (θ0 + 1)2 −θ0 lim B12 (y) = e n→∞ θ0
  • 88. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceMA(q) divergence 1.0 1.0 1.0 1.0 0.8 0.8 0.8 0.8 0.6 0.6 0.6 0.6 0.4 0.4 0.4 0.4 0.2 0.2 0.2 0.2 0.0 0.0 0.0 0.0 1 2 1 2 1 2 1 2 Evolution [against ] of ABC Bayes factor, in terms of frequencies of visits to models MA(1) (left) and MA(2) (right) when equal to 10, 1, .1, .01% quantiles on insufficient autocovariance distances. Sample of 50 points from a MA(2) with θ1 = 0.6, θ2 = 0.2. True Bayes factor equal to 17.71.
  • 89. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceMA(q) divergence 1.0 1.0 1.0 1.0 0.8 0.8 0.8 0.8 0.6 0.6 0.6 0.6 0.4 0.4 0.4 0.4 0.2 0.2 0.2 0.2 0.0 0.0 0.0 0.0 1 2 1 2 1 2 1 2 Evolution [against ] of ABC Bayes factor, in terms of frequencies of visits to models MA(1) (left) and MA(2) (right) when equal to 10, 1, .1, .01% quantiles on insufficient autocovariance distances. Sample of 50 points from a MA(1) model with θ1 = 0.6. True Bayes factor B21 equal to .004.
  • 90. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceFurther comments ‘There should be the possibility that for the same model, but different (non-minimal) [summary] statistics (so ∗ different η’s: η1 and η1 ) the ratio of evidences may no longer be equal to one.’ [Michael Stumpf, Jan. 28, 2011, ’Og] Using different summary statistics [on different models] may indicate the loss of information brought by each set but agreement does not lead to trustworthy approximations.
  • 91. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceThe only safe cases Besides specific models like Gibbs random fields, using distances over the data itself escapes the discrepancy... [Toni & Stumpf, 2010;Sousa et al., 2009]
  • 92. ABC Methods for Bayesian Model Choice ABC for model choice Generic ABC model choiceThe only safe cases Besides specific models like Gibbs random fields, using distances over the data itself escapes the discrepancy... [Toni & Stumpf, 2010;Sousa et al., 2009] ...and so does the use of more informal model fitting measures [Ratmann, Andrieu, Richardson and Wiujf, 2009]