Fetching the paper…
Reading the bibliography…
A central problem in unsupervised deep learning is how to find useful representations of high-dimensional data, sometimes called "disentanglement".
The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICA
Gresele, L., Rubenstein, P. K., Mehrjou, A., Locatello, F., and Schölkopf, B · 1905
Earlier work this paper cites.
Kobyzev, I., Prince, S. J. D., and Brubaker, M. A. (2020). Normalizing Flows: An Introduction and Review of Current Methods · 1908
Earlier work this paper cites.
Revue de l’Institut International de Statistique ( 2–8)
Darmois, G. (1953). Analyse générale des liaisons stochastiques: Etude particulière de l’analyse factorielle linéaire · 1953
Earlier work this paper cites.
Signal Processing 24 , 1–10
Jutten, C., and Hérault, J. (1991). Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture · 1991
Earlier work this paper cites.
IEEE Trans. on Circuits and Systems 38 , 499–509
Tong, L., Liu, R.-W., Soon, V. C., and Huang, Y.-F. (1991). Indeterminacy and identifiability of blind identification · 1991
Earlier work this paper cites.
Neural Computation 3 , 194–200
Földiák, P. (1991). Learning invariance from transformation sequences · 1991
Earlier work this paper cites.
Computational Linguistics 19 , 313–330
Marcus, M., Santorini, B., and Marcinkiewicz, M. A. (1993). Building a large annotated corpus of English: The Penn Treebank · 1993
Earlier work this paper cites.
Signal processing 36 , 287–314
Comon, P. (1994). Independent component analysis, a new concept? · 1994
Earlier work this paper cites.
Science 269 , 1860–1863
Hecht-Nielsen, R. (1995). Replicator neural networks for universal optimal source coding · 1995
Earlier work this paper cites.
Neural Networks 8 , 411–419
Matsuoka, K., Ohya, M., and Kawamoto, M. (1995). A neural net for blind separation of nonstationary signals · 1995
Earlier work this paper cites.
Neural Computation 8 , 773–786. doi: 10.1162/neco.1996.8.4.773
Schmidhuber, J., Eldracher, M., and Foltin, B. (1996). Semilinear Predictability Minimization Produces Well-Known Feature Detectors · 1996
Earlier work this paper cites.
Int. J. on Neural Systems 8 , 473–484
Back, A. D., and Weigend, A. S. (1997). A first application of independent component analysis to extracting structure from stock returns · 1997
Earlier work this paper cites.
IEEE Trans. on Signal Processing 45 , 434–444
Belouchrani, A., Meraim, K. A., Cardoso, J.-F., and Moulines, E. (1997). A blind source separation technique based on second order statistics · 1997
Earlier work this paper cites.
Proceedings of the IEEE 86 , 2278–2324
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition · 1998
Earlier work this paper cites.
Human brain mapping 6 , 160–188
McKeown, M. J., Makeig, S., Brown, G. G., Jung, T.-P., Kindermann, S. S., Bell, A. J., and Sejnowski, T. J. (1998). Analysis of fMRI data by blind separation into independent spatial components · 1998
Earlier work this paper cites.
Neural Networks 12 , 429–439
Hyvärinen, A., and Pajunen, P. (1999). Nonlinear independent component analysis: Existence and uniqueness results · 1999
Earlier work this paper cites.
IEEE Transactions on Signal Processing 47 , 2807–2820. doi: 10.1109/78.790661
Taleb, A., and Jutten, C. (1999-10). Source separation in post-nonlinear mixtures · 1999
Earlier work this paper cites.
Neural Networks 13 , 411–430
Hyvärinen, A., and Oja, E. (2000). Independent component analysis: Algorithms and applications · 2000
Earlier work this paper cites.
Independent component analysis for financial time series
Oja, E., Kiviluoto, K., and Malaroiu, S · 2000
Earlier work this paper cites.
Astronomy and Astrophysics Supplement Series 147 , 129–138
Nuzillard, D., and Bijaoui, A. (2000). Blind source separation and analysis of multispectral astronomical images · 2000
Earlier work this paper cites.
Independent Component Analysis
Hyvärinen, A., Karhunen, J., and Oja, E · 2001
Earlier work this paper cites.
The three easy routes to independent component analysis: contrasts and geometry
Cardoso, J.-F · 2001
Earlier work this paper cites.
IEEE Trans. Signal Processing 49 , 1837–1848
Pham, D.-T., and Cardoso, J.-F. (2001). Blind separation of instantaneous mixtures of nonstationary sources · 2001
Earlier work this paper cites.
ICA and SOM in text document analysis
Bingham, E., Kuusisto, J., and Lagus, K · 2002
Earlier work this paper cites.
Neural Computation 14 , 715–770
Wiskott, L., and Sejnowski, T. J. (2002). Slow feature analysis: Unsupervised learning of invariances · 2002
Earlier work this paper cites.
The Journal of Machine Learning Research 3 , 1137–1155
Bengio, Y., Ducharme, R., Vincent, P., and Janvin, C. (2003). A neural probabilistic language model · 2003
Earlier work this paper cites.
ICA of functional MRI data: An overview
Calhoun, V. D., Adali, T., Hansen, L. K., Larsen, J., and Pekar, J. J · 2003
Earlier work this paper cites.
Neural Computation 15 , 1089–1124
Harmeling, S., Ziehe, A., Kawanabe, M., and Müller, K.-R. (2003). Kernel-based nonlinear blind source separation · 2003
Earlier work this paper cites.
Arxiv preprint. arXiv:2005.00687
Hu, W., Fey, M., Zitnik, M., Dong, Y., Ren, H., Liu, B., Catasta, M., and Leskovec, J. (2020). Open graph benchmark: Datasets for machine learning on graphs · 2005
Earlier work this paper cites.
Philos. Trans. R. Soc. Lond. B. Biol. Sci. 360 , 1001–13
Beckmann, C. F., DeLuca, M., Devlin, J. T., and Smith, S. M. (2005). Investigations into resting-state connectivity using independent component analysis · 2005
Earlier work this paper cites.
Neuroimage 34 , 1443–1449
Delorme, A., Sejnowski, T., and Makeig, S. (2007). Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis · 2007
Earlier work this paper cites.
arXiv preprint arXiv:2007.10930
Klindt, D., Schott, L., Sharma, Y., Ustyuzhaninov, I., Brendel, W., Bethge, M., and Paiton, D. (2020). Towards nonlinear disentanglement in natural data with temporal sparse coding · 2007
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L · 2009
Earlier work this paper cites.
Biological psychiatry 65 , 22–30
Milne, E., Scope, A., Pascalis, O., Buckley, D., and Makeig, S. (2009). Independent component analysis reveals atypical electroencephalographic activity during visual perception in individuals with autism · 2009
Earlier work this paper cites.
Natural Image Statistics
Hyvärinen, A., Hurri, J., and Hoyer, P. O · 2009
Earlier work this paper cites.
Deep learning from temporal coherence in video
Mobahi, H., Collobert, R., and Weston, J · 2009
Cited alongside, same era.
NeuroImage 49 , 257–271
Hyvärinen, A., Ramkumar, P., Parkkonen, L., and Hari, R. (2010). Independent component analysis of short-time Fourier transforms for spontaneous EEG/MEG analysis · 2010
Cited alongside, same era.
Source separation and higher-order causal analysis of MEG and EEG
Zhang, K., and Hyvärinen, A · 2010
Cited alongside, same era.
Learning word vectors for sentiment analysis
Maas, A., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., and Potts, C · 2011
Cited alongside, same era.
The million song dataset
Bertin-Mahieux, T., Ellis, D. P., Whitman, B., and Lamere, P · 2011
Cited alongside, same era.
IEEE Transactions on Audio, Speech, and Language Processing 20 , 30–42
Dahl, G. E., Yu, D., Deng, L., and Acero, A. (2011). Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition · 2011
Isolating Sources of Disentanglement in Variational Autoencoders
Chen, R. T. Q., Li, X., Grosse, R. B., and Duvenaud, D. K · 2018
Later among the works it cites.
Arxiv preprint. arXiv:1812.02833
Mathieu, E., Rainforth, T., Siddharth, N., and Teh, Y. W. (2018-12-06). Disentangling Disentanglement in Variational Autoencoders · 2018
Later among the works it cites.
Kim, H., and Mnih, A · 2018
Later among the works it cites.
IEEE transactions on pattern analysis and machine intelligence 40 , 2897–2905
Achille, A., and Soatto, S. (2018). Information dropout: Learning optimal representations through noisy computation · 2018
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Conversational speech transcription using context-dependent deep neural networks
Seide, F., Li, G., and Yu, D · 2011
Cited alongside, same era.
Proc. National Academy of Sciences (USA) 108 , 16783–16788
Brookes, M., Woolrich, M., Luckhoo, H., Price, D., Hale, J., Stephenson, M., Barnes, G., Smith, S., and Morris, P. (2011). Investigating the electrophysiological basis of resting state networks using magnetoencephalography · 2011
Cited alongside, same era.
Neural computation 23 , 1661–1674
Vincent, P. (2011). A connection between score matching and denoising autoencoders · 2011
Cited alongside, same era.
Communications of the ACM 60 , 84–90. doi: 10.1145/3065386
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks · 2012
Cited alongside, same era.
J. of Machine Learning Research 13 , 307–361
Gutmann, M. U., and Hyvärinen, A. (2012). Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics · 2012
Cited alongside, same era.
Learning temporal coherent features through life-time sparsity
Springenberg, J. T., and Riedmiller, M · 2012
Cited alongside, same era.
Oord, A. v. d., Li, Y., and Vinyals, O. (2018). Representation learning with contrastive predictive coding · 2018
Later among the works it cites.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K · 2019
Later among the works it cites.
Structured Disentangled Representations
Esmaeili, B., Wu, H., Jain, S., Bozkurt, A., Siddharth, N., Paige, B., Brooks, D. H., Dy, J., and Meent, J.-W · 2019
Later among the works it cites.
Auto-encoding total correlation explanation
Gao, S., Brekelmans, R., Ver Steeg, G., and Galstyan, A · 2019
Later among the works it cites.
Challenging common assumptions in the unsupervised learning of disentangled representations
Locatello, F., Bauer, S., Lucic, M., Raetsch, G., Gelly, S., Schölkopf, B., and Bachem, O · 2019
Later among the works it cites.
Nonlinear ICA using auxiliary variables and generalized contrastive learning
Hyvärinen, A., Sasaki, H., and Turner, R · 2019
Later among the works it cites.
NeuroImage 185 , 565–574
Zhigalov, A., Heinilä, E., Parviainen, T., Parkkonen, L., and Hyvärinen, A. (2019). Decoding attentional states for neurofeedback: Mindfulness vs. wandering thoughts · 2019
Later among the works it cites.
Causal discovery with general non-linear relationships using non-linear ICA
Monti, R. P., Zhang, K., and Hyvärinen, A · 2019
Later among the works it cites.
Hidden Markov nonlinear ICA: Unsupervised learning from nonstationary time series
Hälvä, H., and Hyvärinen, A · 2020
Later among the works it cites.
Advances in Neural Information Processing Systems 33 , 7234–7247
Zhou, D., and Wei, X.-X. (2020). Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE · 2020
Later among the works it cites.
Multi-task self-supervised learning for robust speech recognition
Ravanelli, M., Zhong, J., Pascual, S., Swietojanski, P., Monteiro, J., Trmal, J., and Bengio, Y · 2020
Later among the works it cites.
Disentangling identifiable features from noisy data with structured nonlinear ICA
Hälvä, H., Corff, S. L., Lehéricy, L., So, J., Zhu, Y., Gassiat, E., and Hyvärinen, A · 2021
Later among the works it cites.
J. Neural Engineering 18
Banville, H., Chehab, O., Hyvärinen, A., Engemann, D.-A., and Gramfort, A. (2021). Uncovering the structure of clinical EEG signals with self-supervised learning · 2021
Later among the works it cites.
Independent innovation analysis for nonlinear vector autoregressive process
Morioka, H., Hälvä, H., and Hyvärinen, A · 2021
Later among the works it cites.
arXiv preprint arXiv:2101.03288
Song, Y., and Kingma, D. P. (2021). How to train your energy-based models · 2021
Later among the works it cites.
IEEE Transactions on Emerging Topics in Computational Intelligence 5 , 726–742
Zhang, Y., Ti v · 2021
Later among the works it cites.
Advances in neural information processing systems 34 , 28233–28248
Gresele, L., Von Kügelgen, J., Stimper, V., Schölkopf, B., and Besserve, M. (2021). Independent mechanism analysis, a new concept? · 2021
Later among the works it cites.
Contrastive learning inverts the data generating process
Zimmermann, R. S., Sharma, Y., Schneider, S., Bethge, M., and Brendel, W · 2021
Later among the works it cites.
arXiv preprint arXiv:2110.10804
Moran, G. E., Sridhar, D., Wang, Y., and Blei, D. M. (2021). Identifiable variational autoencoders via sparse decoding · 2021
Later among the works it cites.
Journal of Machine Learning Research 23 , 1–61
D’Amour, A., Heller, K., Moldovan, D., Adlam, B., Alipanahi, B., Beutel, A., Chen, C., Deaton, J., Eisenstein, J., Hoffman, M. D. et al. (2022). Underspecification presents challenges for credibility in modern machine learning · 2022
Later among the works it cites.
Estimation of the iVAE model with generative adversarial networks
Luopajärvi, K · 2022
Later among the works it cites.
arXiv preprint arXiv:2208.06406
Buchholz, S., Besserve, M., and Schölkopf, B. (2022). Function classes for identifiable nonlinear independent component analysis · 2022
Later among the works it cites.
arXiv preprint arXiv:2206.10044
Kivva, B., Rajendran, G., Ravikumar, P., and Aragam, B. (2022). Identifiability of deep generative models under mixture priors without auxiliary information · 2022
Later among the works it cites.
Disentanglement via mechanism sparsity regularization: A new principle for nonlinear ICA
Lachapelle, S., Rodriguez, P., Sharma, Y., Everett, K. E., Le Priol, R., Lacoste, A., and Lacoste-Julien, S · 2022
Later among the works it cites.
On finite-sample identifiability of contrastive learning-based nonlinear independent component analysis
Lyu, Q., and Fu, X · 2022
Later among the works it cites.
arXiv preprint arXiv:2302.02672
Hyvärinen, A., Khemakhem, I., and Monti, R. P. (2023). Identifiability of latent-variable and structural-equation models: from linear to nonlinear · 2023
Closest in time.
Annals of Statistics 51 , 487–518
Schell, A., and Oberhauser, H. (2023). Nonlinear independent component analysis for discrete-time and continuous-time signals · 2023
Closest in time.
Connectivity-contrastive learning: Combining causal discovery and representation learning for multimodal data
Morioka, H., and Hyvärinen, A · 2023
Closest in time.
NeuroImage 274
Zhu, Y., Parviainen, T., Heinilä, E., Parkkonen, L., and Hyvärinen, A. (2023). Unsupervised representation learning of spontaneous MEG data with nonlinear ICA · 2023
Closest in time.
Nature 617 , 360–368
Schneider, S., Lee, J. H., and Mathis, M. W. (2023). Learnable latent embeddings for joint behavioural and neural analysis · 2023
Closest in time.
Indeterminacy in generative models: Characterization and strong identifiability
Xi, Q., and Bloem-Reddy, B · 2023
Closest in time.