Fetching the paper…
Reading the bibliography…
We prove identifiability of a broad class of deep latent variable models that (a) have universal approximation capabilities and (b) are the decoders of variational autoencoders that are commonly used in practice.
Analyse des liaisons de probabilité
G. Darmois · 1951
Earlier work this paper cites.
Identifiability of finite mixtures
H. Teicher · 1963
Earlier work this paper cites.
Identifiability of mixtures of exponential families
O. Barndorff-Nielsen · 1965
Earlier work this paper cites.
Identifiability of mixtures of product measures
H. Teicher · 1967
Earlier work this paper cites.
A statistical semantics for causation
J. Pearl and T. S. Verma · 1992
Earlier work this paper cites.
Independent component analysis, a new concept?
P. Comon · 1994
Earlier work this paper cites.
Nonlinear independent component analysis: Existence and uniqueness results
A. Hyvärinen and P. Pajunen · 1999
Earlier work this paper cites.
Nonparametric estimation of component distributions in a multivariate mixture
P. Hall and X.-H. Zhou · 2003
Earlier work this paper cites.
Advances in nonlinear blind source separation
C. Jutten, J. Karhunen, et al · 2003
Earlier work this paper cites.
Identifiability of post-nonlinear mixtures
S. Achard and C. Jutten · 2005
Earlier work this paper cites.
Semiparametric estimation of a two-component mixture model
L. Bordes, S. Mottelet, and P. Vandekerkhove · 2006
Earlier work this paper cites.
Inference for mixtures of symmetric distributions
D. R. Hunter, S. Wang, and T. P. Hettmansperger · 2007
Earlier work this paper cites.
Minimal nonlinear distortion principle for nonlinear independent component analysis
K. Zhang and L. Chan · 2008
Earlier work this paper cites.
Identifiability of parameters in latent structure models with many observed variables
E. S. Allman, C. Matias, and J. A. Rhodes · 2009
Earlier work this paper cites.
Learning topic models–going beyond svd
S. Arora, R. Ge, and A. Moitra · 2012
Earlier work this paper cites.
When are overcomplete topic models identifiable? uniqueness of tensor tucker decompositions with structured sparsity
A. Anandkumar, D. J. Hsu, M. Janzamin, and S. M. Kakade · 2013
Earlier work this paper cites.
A practical algorithm for topic modeling with provable guarantees
S. Arora, R. Ge, Y. Halpern, D. Mimno, A. Moitra, D. Sontag, Y. Wu, and M. Zhu · 2013
Earlier work this paper cites.
Warped mixtures for nonparametric cluster shapes
T. Iwata, D. Duvenaud, and Z. Ghahramani · 2013
Earlier work this paper cites.
Auto-encoding variational bayes
D. P. Kingma and M. Welling · 2013
Earlier work this paper cites.
Stochastic backpropagation and approximate inference in deep generative models
D. J. Rezende, S. Mohamed, and D. Wierstra · 2014
Earlier work this paper cites.
Understanding image representations by measuring their equivariance and equivalence
K. Lenc and A. Vedaldi · 2015
Earlier work this paper cites.
Deep unsupervised clustering with gaussian mixture variational autoencoders
N. Dilokthanakul, P. A. Mediano, M. Garnelo, M. C. Lee, H. Salimbeni, K. Arulkumaran, and M. Shanahan · 2016
Earlier work this paper cites.
Graphs for margins of bayesian networks
R. J. Evans · 2016
Earlier work this paper cites.
Inference in finite state space non parametric hidden markov models and applications
É. Gassiat, A. Cleynen, and S. Robin · 2016
Earlier work this paper cites.
Unsupervised feature extraction by time-contrastive learning and nonlinear ica
A. Hyvarinen and H. Morioka · 2016
Earlier work this paper cites.
Variational deep embedding: An unsupervised and generative approach to clustering
Z. Jiang, Y. Zheng, H. Tan, B. Tang, and H. Zhou · 2016
Cited alongside, same era.
Composing graphical models with neural networks for structured representations and fast inference
M. J. Johnson, D. K. Duvenaud, A. Wiltschko, R. P. Adams, and S. R. Datta · 2016
Cited alongside, same era.
Approximate inference for deep latent gaussian mixtures
E. Nalisnick, L. Hertel, and P. Smyth · 2016
Cited alongside, same era.
Nonlinear ica of temporally dependent stationary sources
A. Hyvarinen and H. Morioka · 2017
Cited alongside, same era.
Parameter identifiability in statistical machine learning: a review
Z.-Y. Ran and B.-G. Hu · 2017
Cited alongside, same era.
Neural discrete representation learning
A universal approximation theorem of deep neural networks for expressing probability distributions
Y. Lu and J. Lu · 2020
Later among the works it cites.
Generalization properties of optimal transport gans with latent distribution learning
G. Luise, M. Pontil, and C. Ciliberto · 2020
Later among the works it cites.
Measurement dependence inducing latent causal models
A. Markham and M. Grosse-Wentrup · 2020
Later among the works it cites.
Consistent estimation of identifiable nonparametric mixture models from grouped observations
A. Ritchie, R. A. Vandermeulen, and C. Scott · 2020
Later among the works it cites.
Coupling-based invertible neural networks are universal diffeomorphism approximators
T. Teshima, I. Ishikawa, K. Tojo, K. Oono, M. Ikeda, and M. Sugiyama · 2020
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
A. Van Den Oord, O. Vinyals, et al · 2017
Cited alongside, same era.
Lagging inference networks and posterior collapse in variational autoencoders
J. He, D. Spokoyny, G. Neubig, and T. Berg-Kirkpatrick · 2018
Cited alongside, same era.
Learning latent subspaces in variational autoencoders
J. Klys, J. Snell, and R. Zemel · 2018
Cited alongside, same era.
Learning latent superstructures in variational autoencoders for deep multidimensional clustering
X. Li, Z. Chen, L. K. Poon, and N. L. Zhang · 2018
Cited alongside, same era.
Vae with a vampprior
J. Tomczak and M. Welling · 2018
Cited alongside, same era.
Nonlinear ica using auxiliary variables and generalized contrastive learning
A. Hyvarinen, H. Sasaki, and R. Turner · 2019
Cited alongside, same era.
Identifying through flows for recovering latent representations
S. Li, B. Hooi, and G. H. Lee · 2019
Cited alongside, same era.
Failure modes of variational autoencoders and their effects on downstream tasks
Y. Yacoby, W. Pan, and F. Doshi-Velez · 2020
Later among the works it cites.
Revisiting model stitching to compare neural representations
Y. Bansal, P. Nakkiran, and B. Barak · 2021
Later among the works it cites.
Similarity and matching of neural network representations
A. Csiszárik, P. Kőrösi-Szabó, Á. Matszangosz, G. Papp, and D. Varga · 2021
Later among the works it cites.
Multi-facet clustering variational autoencoders
F. Falck, H. Zhang, M. Willetts, G. Nicholson, C. Yau, and C. C. Holmes · 2021
Later among the works it cites.
Independent mechanism analysis, a new concept?
L. Gresele, J. Von Kügelgen, V. Stimper, B. Schölkopf, and M. Besserve · 2021
Later among the works it cites.
Disentangling identifiable features from noisy data with structured nonlinear ica
H. Hälvä, S. L. Corff, L. Lehéricy, J. So, Y. Zhu, E. Gassiat, and A. Hyvarinen · 2021
Later among the works it cites.
Learning latent causal graphs via mixture oracles
B. Kivva, G. Rajendran, P. Ravikumar, and B. Aragam · 2021
Later among the works it cites.
An identifiable double vae for disentangled representations
G. Mita, M. Filippone, and P. Michiardi · 2021
Later among the works it cites.
Identifiable variational autoencoders via sparse decoding
G. E. Moran, D. Sridhar, Y. Wang, and D. M. Blei · 2021
Later among the works it cites.
On linear identifiability of learned representations
G. Roeder, L. Metz, and D. Kingma · 2021
Later among the works it cites.
Toward causal representation learning
B. Schölkopf, F. Locatello, S. Bauer, N. R. Ke, N. Kalchbrenner, A. Goyal, and Y. Bengio · 2021
Later among the works it cites.
Visual representation learning does not generalize strongly within the same domain
L. Schott, J. von Kügelgen, F. Träuble, P. Gehler, C. Russell, M. Bethge, B. Schölkopf, F. Locatello, and W. Brendel · 2021
Later among the works it cites.
An embedding of relu networks and an analysis of their identifiability
P. Stock and R. Gribonval · 2021
Later among the works it cites.
Posterior collapse and latent variable non-identifiability
Y. Wang, D. Blei, and J. P. Cunningham · 2021
Later among the works it cites.
I don’t need 𝐮 \mathbf{u} : Identifiable non-linear ica without side information
M. Willetts and B. Paige · 2021
Later among the works it cites.
Nonlinear ica using volume-preserving transformations
X. Yang, Y. Wang, J. Sun, X. Zhang, S. Zhang, Z. Li, and J. Yan · 2021
Later among the works it cites.
Contrastive learning inverts the data generating process
R. S. Zimmermann, Y. Sharma, S. Schneider, M. Bethge, and W. Brendel · 2021
Later among the works it cites.
Weakly supervised causal representation learning
J. Brehmer, P. De Haan, P. Lippe, and T. Cohen · 2022
Closest in time.
Universal approximation property of invertible neural networks
I. Ishikawa, T. Teshima, K. Tojo, K. Oono, M. Ikeda, and M. Sugiyama · 2022
Closest in time.