A. A. Alemi, B. Poole, I. Fischer, J. V. Dillon, R. A. Saurous et al., Fixing a Broken ELBO, 2017.

G. Andrew, R. Arora, J. Bilmes, and K. Livescu, Deep Canonical Correlation Analysis, Proc. Mach. Learn. Res, vol.28, issue.3, pp.1247-1255, 2013.

J. Ashburner and K. J. Friston, Voxel-based morphometry-the methods, Neuroimage, vol.11, issue.6, pp.805-826, 2000.

D. M. Blei, A. Kucukelbir, and J. D. Mcauliffe, Variational Inference: A Review for Statisticians, 2016.

Y. Burda, R. Grosse, and R. Salakhutdinov, Importance Weighted Autoencoders, 2015.

B. Dubois, H. H. Feldman, C. Jacova, H. Hampel, J. L. Molinuevo et al., Advancing research diagnostic criteria for Alzheimer's disease: the IWG-2 criteria, Lancet. Neurol, vol.13, issue.6, pp.614-643, 2014.

S. Haufe, F. Meinecke, K. Görgen, S. Dähne, J. Haynes et al., On the interpretation of weight vectors of linear models in multivariate neuroimaging, Neuroimage, vol.87, pp.96-110, 2014.

H. Hotelling, Relations Between Two Sets of Variates, Biometrika, vol.28, issue.3/4, p.321, 1936.

S. Huang, M. Lee, and C. K. Hsiao, Nonlinear measures of association with kernel canonical correlation analysis and applications, J. Stat. Plan. Inference, vol.139, issue.7, pp.2162-2174, 2009.

C. R. Jack, D. A. Bennett, K. Blennow, M. C. Carrillo, B. Dunn et al., Toward a biological definition of Alzheimer's disease. Alzheimer's Dement, vol.14, pp.535-562, 2018.

J. R. Kettenring, Canonical analysis of several sets of variables, Biometrika, vol.58, issue.3, pp.433-451, 1971.

Y. Kim, S. Wiseman, A. C. Miller, D. Sontag, and A. M. Rush, Semi-Amortized Variational Autoencoders, 2018.

D. P. Kingma, J. Ba, and . Adam, A Method for Stochastic Optimization. CoRR, abs/1412, vol.6, 2014.

D. P. Kingma and M. Welling, Auto-Encoding Variational Bayes, Proc. 2nd Int. Conf. Learn. Represent. (ICLR2014), 2014.

D. P. Kingma, T. Salimans, and M. Welling, Variational Dropout and the Local Reparameterization Trick, Adv. Neural Inf. Process. Syst, vol.28, pp.2575-2583

A. Klami and S. Kaski, Local dependent components, Proceedings of ICML 2007, the 24th International Conference on Machine Learning, pp.425-432, 2007.

A. Klami, V. Seppo, and S. Kaski, Bayesian Canonical Correlation Analysis, J. Mach. Learn. Res, vol.14, pp.965-1003, 2013.

J. Liu and V. D. Calhoun, A review of multivariate analyses in imaging genetics, Front. Neuroinform, vol.8, p.29, 2014.

Y. Luo, D. Tao, K. Ramamohanarao, C. Xu, W. et al., Tensor Canonical Correlation Analysis for Multi-View Dimension Reduction, IEEE Trans. Knowl. Data Eng, vol.27, issue.11, pp.3111-3124, 2015.

D. Molchanov, A. Ashukha, and D. Vetrov, Variational Dropout Sparsifies Deep Neural Networks. arXiv, 2017.

A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang et al., Automatic differentiation in pytorch, 2017.

D. J. Rezende, S. Mohamed, and D. Wierstra, Stochastic Backpropagation and Approximate Inference in Deep Generative Models, 2014.

N. Srivastava, H. Geoffrey, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, Dropout: A Simple Way to Prevent Neural Networks from Overfitting, J. Mach. Learn. Res, vol.15, pp.1929-1958, 2014.

N. Tzourio-mazoyer, B. Landeau, D. Papathanassiou, F. Crivello, O. Etard et al., Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain, Neuroimage, vol.15, issue.1, pp.273-289, 2002.

L. Wan, M. Zeiler, S. Zhang, Y. Le-cun, F. et al., Regularization of Neural Networks using DropConnect, Proc. 30th Int. Conf. Mach. Learn, pp.1058-1066, 2013.

S. Wang and C. Manning, Fast dropout training, Proc. 30th Int. Conf, vol.28, pp.118-126, 2013.

S. Yeung, A. Kannan, Y. Dauphin, and L. Fei-fei, Tackling Over-pruning in Variational Autoencoders, 2017.

, ? the French government, through the UCAJEDI Investments in the Future project managed by the National Research Agency (ANR) with the reference number

, ? the grant AAP Santé 06 2017-260 DGA-DSH, and by the Inria Sophia Antipolis -Méditerranée, NEF" computation cluster

, ? Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012), ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association

, Alzheimer's Drug Discovery Foundation

, Araclon Biotech

I. Bioclinica and . Biogen,

I. Cerespir and . Cogstate,

E. Inc, Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd, Johnson & Johnson Pharmaceutical Research & Development LLC

. Merck-&-co and . Inc, NeuroRx Research

, Novartis Pharmaceuticals Corporation

, The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California