betaFeedback

WorksMathematics

Identifiability of latent variable models with flexible latent distributions

Abstract

Latent variable models are popularly used to characterize dependence among many observed variables through underlying latent variables. Recent advances in statistics and machine learning methods have encouraged growing interest in studying latent variable models with flexible latent distributions that capture complex latent structures. This flexibility, however, raises a fundamental question of whether model parameters can be identified when the latent distribution is unknown and must itself be learned. In this paper, we show that exact identifiability fails almost everywhere, in the sense that distinct but arbitrarily close pairs of model parameters and latent distributions can yield exactly the same distribution for the observed variables. Nonetheless, the resulting identification ambiguity is small. In particular, we prove that the identification ambiguity, measured by the diameter of the set of parameters inducing the same marginal distribution, vanishes at a superpolynomial rate of exp⁡{−c(log⁡p)2}\exp\{-c(\log p)^2\} as the number of observed variables pp grows. Building on this result, we show that the failure of exact identifiability need not preclude consistent estimation or valid inference of the model parameters and latent distribution. These results suggest that, when many variables are observed, the identifiability issue is far less of an obstacle to estimation and inference in latent variable models than is commonly expected.

Introduction

Advances in machine learning have greatly expanded our ability to learn complex distributions [19, 31, 45] (Ho et al. 2020). These advances have, in turn, stimulated interest in flexible latent distributions within latent variable models, where the distribution of the observed variables is determined jointly by the conditional response model and the latent distribution. Moving beyond conventional Gaussian latent distributions allows such models to capture richer forms of population heterogeneity, and thereby to support inference on complex latent structures across the social, economic, and health sciences [4, 5, 39] (Xu et al. 2023). At the same time, these developments raise a fundamental question of whether model parameters remain identifiable when the latent distribution is left unrestricted, a property on which estimation, inference, and interpretation all depend.

This identifiability question is especially relevant under nonlinear models, where the model parameters and the latent distribution jointly affect the observed responses through a nonlinear relationship. As a representative case, we consider a binary response vector X∈{0,1}pX \in\{0,1\}^{p}, whose distribution depends on a dd-dimensional latent random vector Z∈RdZ \in\mathbb{R}^{d}. Conditional on ZZ, the components {Xj}j≤p\{X_j\}_{j\le p} are independent, with

P(Xj=1∣Z=z)=f(βj+αjTz),for j=1,…,p,(1)\mathbb{P}(X_j = 1 \mid Z = z) = f(\beta_j + \alpha_j^{\mathsf{T}}z), \quad\text{for } j = 1,\ldots,p, \tag*{(1)}

where f:R→(0,1)f:\mathbb{R}\to(0,1) is a specified response function. The model parameters are denoted by θ=(A,β)\theta=(A,\beta), where A=(α1,…,αp)T∈Rp×dA=(\alpha_1,\ldots,\alpha_p)^{\mathsf{T}}\in\mathbb{R}^{p\times d} and β=(β1,…,βp)T∈Rp\beta=(\beta_1,\ldots,\beta_p)^{\mathsf{T}}\in\mathbb{R}^{p}. Since ZZ is unobserved, the distribution of XX is obtained by integrating out ZZ with respect to its latent distribution GG. Specifically, for x∈{0,1}px\in\{0,1\}^{p},

pθ,G(X=x)=∫Rd∏j=1p{f(βj+αjTz)}xj{1−f(βj+αjTz)}1−xj dG(z).(2)p_{\theta,G}(X=x)=\int_{\mathbb{R}^{d}}\prod_{j=1}^{p}\{f(\beta_j+\alpha_j^{\mathsf{T}}z)\}^{x_j}\{1-f(\beta_j+\alpha_j^{\mathsf{T}}z)\}^{1-x_j}\,dG(z). \tag*{(2)}

We denote the corresponding marginal distribution of the observed variable XX by Pθ,GP_{\theta,G}, which depends on both the model parameter and latent distribution. This model covers several important classes of latent models:

  1. Item response theory. In item response theory and related measurement models for educational and psychological assessment, ZZ represents unobserved abilities, attitudes, or psychological traits [47], and its distribution GG can be asymmetric, multimodal, and dependent to capture rich population heterogeneity [56]. Parameter αj\alpha_j describes how strongly and in which directions item jj responds to variation in these latent traits.

  1. Latent-class models. When GG has finite support, (1) becomes a latent class model given by a finite mixture of product Bernoulli distributions [1, 20, 36]. The support points of GG represent latent classes with distinct response profiles, while their probability masses give the corresponding population proportions [9]. Here, αj\alpha_j describes how the response probability for item jj varies across these latent classes.

  1. Generative models. Under the logistic link f(⋅)f(\cdot), for instance, model (1) describes the Bernoulli observation layer used in sigmoid belief networks and related generative models [24, 31, 59]. In this setting, ZZ is the hidden representation, GG is its distribution, and (A,β)(A,\beta) parameterize the observation layer.

A fundamental issue shared by these applications is model identifiability. Formally, identifiability requires that, for any (θ,G)(\theta,G) and (θ~,G~)(\tilde{\theta},\tilde{G}) in the admissible parameter space,

Pθ,G=Pθ~,G~⟹θ=θ~.P_{\theta,G}=P_{\tilde{\theta},\tilde{G}} \quad\Longrightarrow\quad\theta=\tilde{\theta}.

Identifiability plays a fundamental role in both the theory and practice of latent variable modeling. Theoretically, it is a prerequisite for consistent parameter estimation and valid statistical inference. Practically, without identifiability, the data cannot distinguish between parameters that induce the same observed distribution, leaving the interpretation of the estimated model ambiguous. We therefore ask

(Q1) Are the model parameter θ\theta and latent distribution GG identifiable in (1)?

(Q2) If not, is reliable estimation still possible?

The primary difficulty in answering this is to uniquely disentangle these two components from the marginal distribution Pθ,GP_{\theta,G}. Since GG enters the marginal distribution via integration, the resulting ambiguity is of a different and less tractable nature than the familiar indeterminacies in θ\theta. To make the problem more tractable, most existing studies examine identifiability under additional restrictions, typically on GG. For instance, conventional analyses often take GG to be a dd-dimensional Gaussian distribution, in which case the identifiability issue reduces to affine indeterminacies that can be resolved through appropriate constraints [3, 20]. However, a Gaussian specification may fail to capture asymmetry, multimodality, and other features of heterogeneous latent populations [39, 65].

Beyond the Gaussian case, several studies allow non-Gaussian latent distributions under other restrictions. For example, Allman et al. [1] consider latent distributions with a known finite number of support points and establish generic identifiability. Restrictions on the response structure are also considered, for instance by Xu [63] and Gu and Xu [21], to establish identifiability of restricted latent class models. In deep generative models, identifiability is often achieved using auxiliary variables, such as time segments or class labels [26, 30], or mixture priors on the latent variables [32]. Across these studies, identifiability is established under restrictions that can be difficult to verify in practice. Moreover, these restrictions narrow the model class, leaving open whether identifiability holds when the latent distribution GG is left essentially unrestricted.

In this work, we show that exact identifiability fails for almost every parameter in model (1), answering (Q1) in the negative. This is perhaps unsurprising in light of existing non-identifiability results for the one-dimensional item response theory model [22, 53], yet our result is considerably stronger. For almost every parameter θ\theta and latent distribution GG, we construct alternatives (θ~,G~)(\tilde{\theta},\tilde{G}) satisfying Pθ,G=Pθ~,G~P_{\theta,G}=P_{\tilde{\theta},\tilde{G}}, with θ~≠θ\tilde{\theta}\ne\theta and G~\tilde{G} matching the moments of GG up to any prespecified order. This reveals a fundamental obstacle to identifiability under flexible latent distributions that finitely many moment conditions on GG cannot remove.

The more surprising finding is the superpolynomial rate at which this ambiguity vanishes as pp grows. Specifically, under suitable regularity conditions, the discrepancy Dp(θ,θ~)D_p(\theta,\tilde{\theta}) between parameters θ\theta, θ~\tilde{\theta} (defined in (4) below) satisfies

Dp(θ,θ~)≤Cexp⁡{−c(log⁡p)2}wheneverPθ,G=Pθ~,G~,D_p(\theta,\tilde{\theta}) \le C\exp\left\{-c(\log p)^2\right\} \qquad\text{whenever}\qquad P_{\theta,G}=P_{\tilde{\theta},\tilde{G}},

uniformly over admissible (θ,G)(\theta,G), (θ~,G~)(\tilde{\theta},\tilde{G}), for constants C,c>0C,c>0. Thus, the ambiguity decays faster than any polynomial rate of pp and becomes negligible on every polynomial scale. The key technical challenge is to bound Dp(θ,θ~)D_p(\theta,\tilde{\theta}) uniformly over all parameter pairs that yield the same marginal distribution. We address this challenge by constructing high-order approximations based on conditional moments of some carefully selected observed responses, given the rest of the observed responses. The nonlinear link leads to complicated interactions among conditional latent moments of different orders, requiring careful control of the expansion coefficients and remainder. Choosing an expansion order proportional to log⁡p\log p balances the decay of the remainder against the growth of the coefficients in the expansion, yielding the exp⁡{−c(log⁡p)2}\exp\left\{-c(\log p)^2\right\} bound.

This superpolynomial rate provides a basis for answering the second question (Q2). In particular, we show that, even without exact identifiability, estimation errors for both the model parameters and the latent distribution can converge to zero as the sample size and pp diverge. We also provide conditions of valid inference for functionals of the model parameters and population-level quantities defined by the latent distribution. These results provide theoretical justification for the estimability of the model parameters and latent distribution when they are learned jointly (e.g. [4, 44, 61] (Cui, Chen, Wang and Xu 2026; Li and Lee 2026)), in the sense that non-identifiability need not pose an irreducible identifiability barrier to accurate estimation when pp is large.

Related Work

The vanishing identification ambiguity described above can be termed asymptotic identifiability. For unidimensional nonparametric item response models, Douglas [16] established this property for the response functions, and He [23] extended the analysis by relaxing derivative bounds. Both analyses rely on transforming the latent variable to a uniform distribution, which is not applicable in multidimensional settings, and neither quantifies the rate of the vanishing ambiguity. Related questions are studied in panel data models, where pp is the panel length. For instance, Chernozhukov et al. [8] studied the identified sets of average and quantile effects in panel models and showed that they shrink to a point as the panel length increases. In fixed-effects logit models, Davezies et al. [14] derived sharp bounds on average causal effects.

A related literature examines estimation error arising from misspecification of the latent distribution. For logistic mixed-effects models, Neuhaus et al. [41] showed that misspecifying the mixing distribution can lead to inconsistent parameter estimates. For longitudinal models, Rizopoulos et al. [49] showed that the effects of such misspecification vanish for certain parameters as the number of measurements increases. For nonlinear panel models, Arellano and Bonhomme [5] analysed estimation bias under misspecification of the individual-effects. For generalized linear latent variable models, Ma and Genton (2010) developed semiparametric estimating equations under misspecified latent distributions. Our work studies a different identification problem when the latent distribution is unknown and must be estimated. The resulting identification ambiguity is intrinsic to the model, independent of any specific estimation procedure.

Another related literature develops estimation methods under flexible latent distributions, including spline-based densities ([61]), Dirichlet-process mixtures ([44]), kernel density methods ((Li and Lee, 2026)), and normalizing flows ((Cui, Chen, Wang and Xu, 2026)), among others. These studies report accurate estimation of the model parameters when the latent distribution is fitted jointly, but do not provide statistical guarantees for the resulting estimators. This gap cannot be addressed by classical theory for latent variable models, which generally presupposes that the model parameters are identifiable ([36] (Ma and Genton 2010)), a condition that fails for model (1) when GG is unrestricted.

Identifiability is also a central concern in generative modelling and representation learning, where the goal is to uncover the underlying generative mechanisms or latent representations, under a flexible latent distribution. Such questions arise in unsupervised disentanglement ([38]), identifiable generative models ([30] (Xi and Bloem-Reddy 2023)), and causal representation learning ([54]). A prevailing view in this literature is that complex latent structures cannot be identified without additional information or structural constraints, such as auxiliary variables or inductive biases ([30, 38]). Notably, Xi and Bloem-Reddy (2023) characterized the indeterminacies of generative models with flexible nonlinear generators. Their framework requires a continuous data-generating process and thus excludes discrete observations. Our work offers another route that accepts the failure of exact identifiability and instead quantifies the ambiguity that remains.

Notation

For a positive integer nn, let [n]={1,…,n}[n]=\{1,\ldots,n\}. For a finite set SS, ∣S∣|S| denotes its cardinality, and xSx_S is the subvector of xx indexed by SS. For a vector xx, ∥x∥2\lVert x\rVert_2 and ∥x∥∞\lVert x\rVert_\infty denote its ℓ2\ell_2 and ℓ∞\ell_\infty norms, respectively. For a matrix M=(Mij)n×mM=(M_{ij})_{n\times m}, write ∥M∥∞=max⁡i∈[n],j∈[m]∣Mij∣\lVert M\rVert_\infty=\max_{i\in[n],j\in[m]}|M_{ij}| and ∥M∥=max⁡∥x∥=1∥Mx∥\lVert M\rVert=\max_{\lVert x\rVert=1}\lVert Mx\rVert, and write col⁡(M)\operatorname{col}(M) for its column space. Let IdI_d be the d×dd\times d identity matrix. The class C∞C^\infty consists of functions with continuous derivatives of all orders. For a multi-index α=(α1,…,αd)∈{0,1,…}d\alpha=(\alpha_1,\ldots,\alpha_d)\in\{0,1,\ldots\}^d, write ∣a∣=∑k=1dak|a|=\sum_{k=1}^{d}a_k and za=∏k=1dzkakz^a=\prod_{k=1}^{d}z_k^{a_k}. Unless otherwise stated, c,C>0c,C>0 denote constants that may change from line to line.

Problem Setup

In this section, we formalize the model identifiability for (1). The model suffers from the well-known affine indeterminacy as in latent factor models (Anderson, [3]). Specifically, for any μ∈Rd\mu\in\mathbb{R}^d and invertible H∈Rd×dH\in\mathbb{R}^{d\times d}, let G~\widetilde{G} denote the distribution of Z~=H−1(Z−μ)\widetilde{Z}=H^{-1}(Z-\mu) when Z∼GZ\sim G, and set θ~=(AH,β+Aμ)\widetilde{\theta}=(AH,\beta+A\mu). A change of variables then gives Pθ,G=Pθ~,G~P_{\theta,G}=P_{\widetilde{\theta},\widetilde{G}}. We first address this affine indeterminacy, and then formulate identifiability in terms of the remaining ambiguity arising from the interaction between the unknown latent distribution and the model parameters, which is the main focus of our analysis.

First, we adopt a common normalization on the latent variables:

EG(Z)=0,Cov⁡G(Z)=Id.(3)\mathbb{E}_{G}(Z)=0,\qquad\operatorname{Cov}_{G}(Z)=I_d. \tag*{(3)}

When EGZ=m\mathbb{E}_{G}Z=m and Cov⁡G(Z)=Σ≻0\operatorname{Cov}_{G}(Z)=\Sigma\succ0, we can simply take μ=m\mu=m and H=Σ1/2H=\Sigma^{1/2} to yield a standardized latent distribution without changing the marginal distribution. This normalization can also be replaced by more interpretable procedures; see Remark 1 below.

Normalization (3) still leaves a rotational indeterminacy, as for any orthogonal matrix H∈Rd×dH\in\mathbb{R}^{d\times d}, the preceding reparameterization preserves both normalization (3) and the marginal distribution. To account for this, we measure the distance metric between any θ=(A,β)\theta=(A,\beta), θ~=(A~,β~)\widetilde{\theta}=(\widetilde{A},\widetilde{\beta}) as

References

  1. [1]Allman, E. S., Matias, C. and Rhodes, J. A. (2009), ‘Identifiability of parameters in latent structure models with many observed variables’, The Annals of Statistics 37(6A), 3099–3132.DOI
  2. [2]Anandkumar, A., Ge, R., Hsu, D., Kakade, S. M. and Telgarsky, M. (2014), ‘Tensor decompositions for learning latent variable models’, The Journal of Machine Learning Research 15(1), 2773–2832.
  3. [3]Anderson, T. W. (2003), An introduction to multivariate statistical analysis, Wiley New York.
  4. [4]Antonelli, J., Trippa, L. and Haneuse, S. (2016), ‘Mitigating bias in generalized linear mixed models: The case for Bayesian nonparametrics’, Statistical Science 31(1), 80–95.DOI
  5. [5]Arellano, M. and Bonhomme, S. (2009), ‘Robust priors in nonlinear panel data models’, Econometrica 77(2), 489–536.
  6. [6]Bock, R. D. and Aitkin, M. (1981), ‘Marginal maximum likelihood estimation of item parameters: Application of an EM algorithm’, Psychometrika 46(4), 443–459.DOI
  7. [7]Browne, M. W. (2001), ‘An overview of analytic rotation in exploratory factor analysis’, Multivariate Behavioral Research 36(1), 111–150.DOI
  8. [8]Chernozhukov, V., Fernández-Val, I., Hahn, J. and Newey, W. (2013), ‘Average and quantile effects in nonseparable panel models’, Econometrica 81(2), 535–580.
  9. [9]Collins, L. M. and Lanza, S. T. (2013), Latent class and latent transition analysis: With applications in the social, behavioral, and health sciences, John Wiley & Sons.
  10. [13]Cui, C. and Xu, G. (2026b), ‘Marginal maximum likelihood estimation and asymptotic theory for latent variable models in high dimensions’, arXiv preprint arXiv:2609.16653.arxiv.org/abs/2609.16653
  11. [14]Davezies, L., D’Haultfœuille, X. and Laage, L. (2021), ‘Identification and estimation of average causal effects in fixed effects logit models’, arXiv preprint arXiv:2105.00879.arxiv.org/abs/2105.00879
  12. [15]Deville, J.-C. and Särndal, C.-E. (1992), ‘Calibration estimators in survey sampling’, Journal of the American Statistical Association 87(418), 376–382.DOI
  13. [16]Douglas, J. A. (2001), ‘Asymptotic identifiability of nonparametric item response models’, Psychometrika 66(4), 531–540.DOI
  14. [17]Dunson, D. B. and Xing, C. (2009), ‘Nonparametric Bayes modeling of multivariate categorical data’, Journal of the American Statistical Association 104(487), 1042–1051.pubmed.ncbi.nlm.nih.gov/23606777
  15. [18]Fang, G., Guo, J., Xu, X., Ying, Z. and Zhang, S. (2021), ‘Identifiability of bifactor models’, Statistica Sinica 31, 2309–2330.arxiv.org/abs/2012.12196
  16. [19]Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y. (2014), ‘Generative adversarial nets’, Advances in Neural Information Processing Systems 27.
  17. [20]Goodman, L. A. (1974), ‘Exploratory latent structure analysis using both identifiable and unidentifiable models’, Biometrika 61(2), 215–231.DOI
  18. [21]Gu, Y. and Xu, G. (2020), ‘Partial identifiability of restricted latent class models’, The Annals of Statistics 48(4), 2082–2107.arxiv.org/abs/1803.04353
  19. [22]Haberman, S. J. (2005), ‘Identifiability of parameters in item response models with unconstrained ability distributions’, ETS Research Report Series 2005(2), 1–22.DOI
  20. [23]He, Y. (2024), ‘Extended asymptotic identifiability of nonparametric item response models’, Psychometrika 89(3), 958–973.DOI
  21. [24]Hinton, G. E., Dayan, P., Frey, B. J. and Neal, R. M. (1995), ‘The” wake-sleep” algorithm for unsupervised neural networks’, Science 268(5214), 1158–1161.
  22. [26]Hyvarinen, A. and Morioka, H. (2016), ‘Unsupervised feature extraction by time-contrastive learning and nonlinear ica’, Advances in Neural Information Processing Systems 29.arxiv.org/abs/1605.06336
  23. [27]Hyvärinen, A. and Oja, E. (2000), ‘Independent component analysis: algorithms and applications’, Neural Networks 13(4-5), 411–430.pubmed.ncbi.nlm.nih.gov/10946390
  24. [28]Hyvärinen, A. and Pajunen, P. (1999), ‘Nonlinear independent component analysis: Existence and uniqueness results’, Neural Networks 12(3), 429–439.pubmed.ncbi.nlm.nih.gov/12662686
  25. [29]Kaiser, H. F. (1958), ‘The varimax criterion for analytic rotation in factor analysis’, Psychometrika 23(3), 187–200.DOI
  26. [30]Khemakhem, I., Kingma, D., Monti, R. and Hyvarinen, A. (2020), Variational autoencoders and nonlinear ICA: A unifying framework, in ‘International Conference on Artificial Intelligence and Statistics’, PMLR, pp. 2207–2217.arxiv.org/abs/1907.04809
  27. [31]Kingma, D. P. and Welling, M. (2013), ‘Auto-encoding variational bayes’, arXiv preprint arXiv:1312.6114.arxiv.org/abs/1312.6114
  28. [32]Kivva, B., Rajendran, G., Ravikumar, P. and Aragam, B. (2022), ‘Identifiability of deep generative models without auxiliary information’, Advances in Neural Information Processing Systems 35, 15687–15701.arxiv.org/abs/2206.10044
  29. [33]Kolda, T. G. and Bader, B. W. (2009), ‘Tensor decompositions and applications’, SIAM Review 51(3), 455–500.DOI
  30. [34]Lawson, C. L. and Hanson, R. J. (1995), Solving least squares problems, SIAM.
  31. [36]Lindsay, B., Clogg, C. C. and Grego, J. (1991), ‘Semiparametric estimation in the Rasch model and related exponential response models, including a simple latent class model for item analysis’, Journal of the American Statistical Association 86(413), 96–107.DOI
  32. [37]Liu, X., Wallin, G., Chen, Y. and Moustaki, I. (2023), ‘Rotation to sparse loadings using Lᵖ losses and related inference problems’, Psychometrika 88(2), 527–553.
  33. [38]Locatello, F., Bauer, S., Lucic, M., Raetsch, G., Gelly, S., Schölkopf, B. and Bachem, O. (2019), Challenging common assumptions in the unsupervised learning of disentangled representations, in ‘International Conference on Machine Learning’, PMLR, pp. 4114–4124.arxiv.org/abs/1811.12359
  34. [39]Lubke, G. H. and Muthén, B. (2005), ‘Investigating population heterogeneity with factor mixture models.’, Psychological Methods 10(1), 21–39.DOI
  35. [41]Neuhaus, J. M., Hauck, W. W. and Kalbfleisch, J. D. (1992), ‘The effects of mixture distribution misspecification when fitting mixed-effects logistic models’, Biometrika 79(4), 755–762.DOI
  36. [42]Onatski, A. (2012), ‘Asymptotics of the principal components estimator of large factor models with weakly influential factors’, Journal of Econometrics 168(2), 244–258.DOI
  37. [43]Ostrovskii, D. M. and Bach, F. (2021), ‘Finite-sample analysis of M-estimators using self-concordance’, Electronic Journal of Statistics 15(1), 326–391.
  38. [44]Paganin, S., Paciorek, C. J., Wehrhahn, C., Rodríguez, A., Rabe-Hesketh, S. and de Valpine, P. (2023), ‘Computational strategies and estimation performance with Bayesian semiparametric item response theory models’, Journal of Educational and Behavioral Statistics 48(2), 147–188.arxiv.org/abs/2101.11583
  39. [45]Papamakarios, G., Nalisnick, E., Rezende, D. J., Mohamed, S. and Lakshminarayanan, B. (2021), ‘Normalizing flows for probabilistic modeling and inference’, Journal of Machine Learning Research 22(57), 1–64.
  40. [46]Qin, J. and Lawless, J. (1994), ‘Empirical likelihood and general estimating equations’, The Annals of Statistics 22(1), 300–325.
  41. [47]Reckase, M. D. (2009), Multidimensional Item Response Theory, Springer New York, NY.DOI
  42. [48]Reise, S. P. (2012), ‘The rediscovery of bifactor measurement models’, Multivariate Behavioral Research 47(5), 667–696.pubmed.ncbi.nlm.nih.gov/24049214
  43. [49]Rizopoulos, D., Verbeke, G. and Molenberghs, G. (2008), ‘Shared parameter models under random effects misspecification’, Biometrika 95(1), 63–74.DOI
  44. [50]Rohe, K. and Zeng, M. (2023), ‘Vintage factor analysis with Varimax performs statistical inference’, Journal of the Royal Statistical Society Series B: Statistical Methodology 85(4), 1037–1060.arxiv.org/abs/2004.05387
  45. [51]Rota, G.-C. and Taylor, B. D. (1994), ‘The classical umbral calculus’, SIAM Journal on Mathematical Analysis 25(2), 694–711.DOI
  46. [52]Rothenberg, T. J. (1971), ‘Identification in parametric models’, Econometrica: Journal of the Econometric Society 39(3), 577–591.DOI
  47. [53]San Martín, E., Jara, A., Rolin, J.-M. and Mouchart, M. (2011), ‘On the Bayesian nonparametric generalization of IRT-type models’, Psychometrika 76(3), 385–409.DOI
  48. [54]Schölkopf, B., Locatello, F., Bauer, S., Ke, N. R., Kalchbrenner, N., Goyal, A. and Bengio, Y. (2021), ‘Toward causal representation learning’, Proceedings of the IEEE 109(5), 612–634.DOI
  49. [55]Singh, S. and Póczos, B. (2018), ‘Minimax distribution estimation in Wasserstein distance’, arXiv preprint arXiv:1802.08855 .arxiv.org/abs/1802.08855
  50. [56]Skrondal, A. and Rabe-Hesketh, S. (2004), Generalized latent variable modeling: Multilevel, longitudinal, and structural equation models, Chapman and Hall/CRC.
  51. [57]Stein, E. M. and Shakarchi, R. (2003), Complex analysis, Vol. 2, Princeton University Press, Princeton.
  52. [58]Ten Berge, J. M. (1977), ‘Orthogonal Procrustes rotation for two or more matrices’, Psychometrika 42(2), 267–276.DOI
  53. [59]Tomczak, J. and Welling, M. (2018), VAE with a VampPrior, in ‘International Conference on Artificial Intelligence and Statistics’, PMLR, pp. 1214–1223.arxiv.org/abs/1705.07120
  54. [60]Withers, C. S. (1984), ‘Asymptotic expansions for distributions and quantiles with power series cumulants’, Journal of the Royal Statistical Society Series B: Statistical Methodology 46(3), 389–396.
  55. [61]Woods, C. M. and Thissen, D. (2006), ‘Item response theory with estimation of the latent population distribution using spline-based densities’, Psychometrika 71(2), 281–301.DOI
  56. [63]Xu, G. (2017), ‘Identifiability of restricted latent class models with binary responses’, The Annals of Statistics 45(2), 675–707.arxiv.org/abs/1603.04140
  57. [65]Zhang, D. and Davidian, M. (2001), ‘Linear mixed models with flexible distributions of random effects for longitudinal data’, Biometrics 57(3), 795–802.pubmed.ncbi.nlm.nih.gov/11550930

Paper details

vlnc:W_5sgadcwq
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…
Contents