Latest highlights
- Our paper The Manifold Tangent Classifier (S. Rifai, Y.N. Dauphin, P. Vincent, Y. Bengio, X. Muller, NIPS2011) was presented as an oral at NIPS 2011, and won an award (honorable mention) in the outstanding student paper category.
- Our lab won Phase 2
of the Unsupervised
and Transfer Learning Challenge (ranking 4th in Phase 1). Denoising autoencoders and contractive autoencoders were at
the heart of our winning strategy! See our paper describing the approach:
Unsupervised and Transfer Learning Challenge: a Deep Learning Approach.
G. Mesnil, Y. Dauphin, X. Glorot, S. Rifai, Y. Bengio, I. Goodfellow, E. Lavoie, X. Muller, G. Desjardins, D. Warde-Farley, P. Vincent, A. Courville and J. Bergstra. ICML 2011 Workshop on Unsupervisedans Transfer Learning, in JMLR: Workshop and Conference Proceedings 7 (2011) 1–15.
All publications by type
Refereed journal papers
- P. Vincent,
A Connection between Score Matching and Denoising Autoencoders,
Neural Computation, 23(7):1661--1674, 2011.
(Preprint version available as Technical Report 1358, Dept. IRO, Université de Montréal, December 2010). - Y. Bengio, O. Breuleux and P. Vincent,
Quickly Generating Representative Samples from an RBM-Derived Process,
Neural Computation. 23(8): 2058-2073, 2011.
- C. Dugas, N. Chapados, R. Ducharme, X. Saint-Mleux and P. Vincent,
A High-Order Feature Synthesis and Selection Algorithm Applied to Insurance Risk Modelling,
International Journal of Business Intelligence and Data Mining, 6(3):237--258, 2011.
- P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio and P.A.
Manzagol,
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion,
Journal of Machine Learning Research, 11:3371--3408, 2010. - , , , ,
and ,
Why Does Unsupervised Pre-training Help Deep Learning?
Journal of Machine Learning Research, 11:625--660, 2010.
- S. Sonnenburg, M.L. Braun, C.S. Ong, S. Bengio, L.
Bottou, G. Holmes, Y. LeCun, K.R. Müller, F. Pereira, C.E. Rasmussen,
G. Rätsch, B. Schölkopf, A. Smola, P. Vincent, J. Weston, R.C.
Williamson,
The Need for Open Source Software in Machine Learning
Journal of Machine Learning Research, 8:2443--2466, 2007. - Y. Bengio, O. Delalleau, N. Le Roux, J.-F. Paiement, P.
Vincent and M. Ouimet,
Learning Eigenfunctions Links Spectral Embedding and Kernel PCA
Neural Computation, 16(10):2197--2219, 2004.
- Yoshua Bengio, Réjean Ducharme, Pascal Vincent and
Christian Jauvin,
A Neural Probabilistic Language Model
Journal of Machine Learning Research, 3:1137-1155, 2003.
- Pascal Vincent and Yoshua Bengio,
Kernel Matching Pursuit
Machine Learning Journal, 48(1):165-187, 2002.
Refereed conference papers
- S. Rifai, Y.N. Dauphin, P. Vincent, Y. Bengio, X. Muller, The Manifold Tangent Classifier,
In Advances in Neural Information Processing Systems 24 (NIPS2011), pages 2294--2302, 2011.
Presented as an oral at NIPS 2011, won an award (honorable mention) in the outstanding student paper category.
- S. Rifai, G. Mesnil, P. Vincent, X. Muller, Y. Bengio, Y.N. Dauphin, X. Glorot, Higher Order Contractive Auto-Encoder, Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2011), Lecture Notes in Computer Science, 6912/2011:645-660, Springer, 2011.
- S. Rifai, P. Vincent, X. Muller, X. Glorot, Y. Bengio, Contractive Auto-Encoders: Explicit
Invariance During Feature Extraction, Proceedings of the
28th International Conference on Machine Learning (ICML'2011), pages 833-840, ACM, 2011.
- , , and ,
Why Does Unsupervised Pre-training Help Deep Learning?,
In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010), Chia Laguna Resort, Sardinia, Italy, pages 201-208, 2010. - , , , P. Vincent
and O. Delalleau
Tempered Markov Chain Monte Carlo for Training of Restricted Boltzmann Machine,
In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010), Chia Laguna Resort, Sardinia, Italy, pages 145--152, 2010 - , , , and ,
The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training,
In Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS 2009), Clearwater (Florida), USA, pages 153--160, 2009. - , and ,
Deep Learning using Robust Interdependent Codes,
In Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS 2009), Clearwater (Florida), USA, pages 312--319, 2009. - N. Chapados, C. Dugas, P. Vincent, R. Ducharme,
Scoring Models for Insurance Risk Sharing Pool Optimization,
ICDM'08 Workshop Proceedings of the 8th IEEE International Conference on Data Mining (ICDM 2008), pages 97-105, IEEE Computer Society, 2008.
- P. Vincent, H. Larochelle, Y. Bengio, P.A. Manzagol,
Extracting and Composing Robust Features with Denoising Autoencoders
In Proceedings of the 25th International Conference on Machine Learning (ICML'2008), 2008. - Y. Bengio, H. Larochelle, P. Vincent,
Non-Local Manifold Parzen Windows
In Advances in Neural Information Processing Systems 18, 2006. - Y. Bengio, N. Le Roux, P. Vincent, O. Delalleau, P.
Marcotte,
Convex Neural Networks
In Advances in Neural Information Processing Systems 18, pages 123--130, MIT Press, 2006. - Y. Bengio, J.F. Paiement, P. Vincent, O. Delalleau, N. Le
Roux and M. Ouimet,
Out-of-sample extensions for LLE, Isomap, MDS, eigenmaps, and Spectral Clustering
In Advances in Neural Information Processing Systems 16, 2004.
- Pascal Vincent and Yoshua Bengio,
Manifold Parzen Windows
In Advances in Neural Information Processing Systems 15,2003.
See also the following addendum:
Mathematical derivation of LocalGaussian computation for Manifold Parzen, and errata,
Technical Report 1259, Département d'Informatique et Recherche Opérationnelle, Université de Montréal, 2005.
- Pascal Vincent and Yoshua Bengio,
K-Local Hyperplane and Convex Distance Nearest Neighbor Algorithms,
In Advances in Neural Information Processing Systems 14, 2002.
- N. Chapados, Y. Bengio, P. Vincent, J. Ghosn, C. Dugas, I.
Takeuchi, L. Meng,
Estimating Car Insurance Premia: a Case Study in High-Dimensional Data Inference,
In Advances in Neural Information Processing Systems 14, 2002.
- Yoshua Bengio, Réjean Ducharme and Pascal Vincent,
A Neural Probabilistic Language Model,
In Advances in Neural Information Processing Systems 13, 2001.
- Léon Bottou, Patrick Haffner, Yann Le Cun, Paul Howard,
Pascal Vincent, Bill Riemers,
DjVu: Un Système de Compression d'Images pour la Distribution Réticulaire de Documents Numérisés,
(DjVu: An image compression system for distributing scanned document on the Internet).
In Actes de la Conférence Internationale Francophone sur l'Ecrit et le Document, Lyon, France, July 2000.
- Pascal Vincent and Yoshua Bengio,
A Neural Support Vector Network Architecture with Adaptive Kernels,
In Proceedings of the International Joint Conference on Neural Networks, Como, Italy, July 2000.
- Patrick Haffner, Yann Le Cun, Léon Bottou, Paul Howard,
Pascal Vincent, Bill Riemers,
Color Documents on the Web with DjVu
In Proceedings of the International Conference on Image Processing, vol 1, pp 239-243, Kobe, Japan, October 1999.
Book chapters
- , , , ,
and ,
Spectral Dimensionality Reduction,
In Feature Extraction, Foundations and Applications, Springer, 2006 - C. Dugas, N. Chapados, Y. Bengio, P. Vincent, G. Denoncourt
et C. Fournier.
Neural Networks Applied to Automobile Insurance Ratemaking
In Intelligent and Other Computational Techniques in Insurance: Theory and Applications,
edited by L. Jain and A.F. Shapiro, World Scientific, 2003.
Thesis (in French)
- Pascal Vincent,
Modèles à Noyaux à Structure Locale,
Thèse de Doctorat, Département d'Informatique et Recherche Opérationnelle, Université de Montréal, Octobre 2003.
Other publications and presentations
- C. Dugas, Y. Bengio, N. Chapados, P. Vincent, G.
Denoncourt, and C. Fournier,
Statistical Learning Algorithms Applied to Automobile Insurance Ratemaking
CAS Forum, 1(1):179-214, Winter 2003. - Yoshua Bengio, Nicolas Chapados, Charles Dugas, Joumana
Ghosn, Ichiro Takeuchi, and Pascal Vincent,
High-dimensional data inference for automobile insurance premia estimation.
Presented at the 2001 MITACS Annual Meeting, Montreal, 2001.
Technical reports
- P. Vincent,
A connection between Score Matching and Denoising Autoencoders
Technical Report 1358, Département d'Informatique et Recherche Opérationnelle, Université de Montréal, December 2010. - , and ,
Unlearning for Better Mixing
Technical Report 1349, Département d'Informatique et Recherche Opérationnelle, Université de Montréal, November 2010. - , , , and ,
Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines,
Technical Report 1345,Département d'Informatique et de Recherche Opérationnelle, Université de Montréal, 2009 - P. Vincent, H. Larochelle, Y. Bengio and P.A. Manzagol,
Extracting and Composing Robust Features with Denoising Autoencoders,
Technical Report 1316, Département d'Informatique et Recherche Opérationnelle, Université de Montréal, February 2008. - Y. Bengio, N. Le Roux, P. Vincent, O. Delalleau and P.
Marcotte,
Convex Neural Networks,
Technical Report 1263, Département d'Informatique et Recherche Opérationnelle, Université de Montréal, 2005.
- Pascal Vincent,
Mathematical derivation of LocalGaussian computation for Manifold Parzen, and errata,
Technical Report 1259, Département d'Informatique et Recherche Opérationnelle, Université de Montréal, 2005.
- Y. Bengio, J-F. Paiement, and P. Vincent,
Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering.
Technical Report 1238, Département d'informatique et recherche opérationnelle, Université de Montréal, 2003. - Y. Bengio, P. Vincent, J-F. Paiement,
O. Delalleau, M. Ouimet, and N. Le Roux,
Spectral Clustering and Kernel PCA are Learning Eigenfunctions.
Technical Report 1239, Département d'informatique et recherche opérationnelle, Université de Montréal, 2003. - Y. Bengio, P. Vincent, and J.F. Paiement,
Learning Eigenfunctions of Similarity: Linking Spectral Clustering and Kernel PCA.
Technical Report 1232, Département d'informatique et recherche opérationnelle, Université de Montréal, 2003. - P. Vincent and Y. Bengio,
Locally Weighted Full Covariance Gaussian Density Estimation.
Technical Report 1240, Département d'informatique et recherche opérationnelle, Université de Montréal, 2003. - Nicolas Chapados, Yoshua Bengio, Pascal Vincent, Joumana
Ghosn, Charles Dugas, Ichiro Takeuchi, and Linyan Meng.
Estimating car insurance premia: a case study in high-dimensional data inference.
Technical Report 1199, Département d'informatique et recherche opérationnelle, Université de Montréal, 2001. - Pascal Vincent and Yoshua Bengio,
K-Local Hyperplane and Convex Distance Nearest Neighbor Algorithms.
Technical Report 1197, Département d'informatique et recherche opérationnelle, Université de Montréal, 2001. - Yoshua Bengio, Réjean Ducharme, and Pascal Vincent,
A Neural Probabilistic Language Model.
Technical Report 1178, Département d'informatique et recherche opérationnelle, Université de Montréal, 2000. - Pascal Vincent and Yoshua Bengio,
Kernel Matching Pursuit,
Technical Report 1179, Département d'Informatique et Recherche Opérationnelle, Université de Montréal, 2000.
- P. Haffner, L. Bottou, J. Bromley, C.J.C. Burges, T.
Cauble, Y. Le Cun, C. Nohl, C. Stanton, C. Stenard, P. Vincent,
The HCAR50 check amount reading system
Technical Report Lucent Technologies, Bell Labs Innovation, 1996.
