Olivier Delalleau


photo de delallea Email: delallea@iro.REMOVETHIS.umontreal.ca
LinkedIn: www.linkedin.com/in/odelalleau
Phone: My home phone number can be found for example on the following websites (whose access is restricted):
Polytechique.org, TelecomParis.org, LISA directory.

Found me! It wasn't too hard, was it?

Journal & Conference papers, Book chapters

Beyond Skill Rating: Advanced Matchmaking in Ghost Recon Online (2012) O.Delalleau, E. Contal, E. Thibodeau-Laufer, R. Chandias Ferrari, Y. Bengio and F. Zhang. In IEEE Transactions on Computational Intelligence and AI in Games, 4(3):167-177. [paper(pdf) | ref(bibtex)]

Shallow vs. Deep Sum-Product Networks (2011) O. Delalleau and Y. Bengio. In Advances in Neural Information Processing Systems 24, pages 666-674. [paper(pdf) | poster(pdf) | ref(bibtex)]

On the Expressive Power of Deep Architectures (2011) Y. Bengio and O. Delalleau. In Proceedings of the 22nd International Conference on Algorithmic Learning Theory [paper(pdf) | ref(bibtex)]

Detonation Classification from Acoustic Signature with the Restricted Boltzmann Machine (2011) Y. Bengio, N. Chapados, O. Delalleau, H. Larochelle, X. Saint-Mleux, C. Hudon and J. Louradour. To appear in Computational Intelligence [paper(pdf)]

Parallel Tempering for Training of Restricted Boltzmann Machines (2010), G. Desjardins, A. Courville, Y. Bengio, P. Vincent and O. Delalleau. In Teh, Y. W. and Titterington, M., editors, Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, May 13-15, 2010, Chia Laguna Resort, Sardinia, Italy, pages 145-152 [paper(pdf) | ref(bibtex)]

Decision Trees do not Generalize to New Variations (2010), Y. Bengio, O. Delalleau and C. Simard. Computational Intelligence, 26(4): 449-467 [paper(pdf) | ref(bibtex)]

Statistical Machine Learning Algorithms for Target Classification from Acoustic Signature (2009) V. Mirelli, S. Tenney, Y. Bengio, N. Chapados and O. Delalleau. In MSS Battlespace Acoustic and Magnetic Sensors, Laurel, MD [paper(pdf) | poster(pdf) | ref(bibtex)]

Justifying and Generalizing Contrastive Divergence (2009), Y. Bengio and O. Delalleau. Neural Computation, 21(6): 1601-1621 [paper(pdf) | paper(ps.gz) | ref(bibtex)]

Large-Scale Algorithms (2006), O. Delalleau, Y. Bengio and N. Le Roux. In Chapelle, O., Schölkopf, B. and Zien, A., editors, Semi-Supervised Learning, pages 333-341, MIT Press [chapter(pdf) | chapter(ps.gz) | ref(bibtex)]

Label Propagation and Quadratic Criterion (2006), Y. Bengio, O. Delalleau and N. Le Roux. In Chapelle, O., Schölkopf, B. and Zien, A., editors, Semi-Supervised Learning, pages 193-216, MIT Press [chapter(pdf) | chapter(ps.gz) | ref(bibtex)]

Spectral Dimensionality Reduction (2006), Y. Bengio, O. Delalleau, N. Le Roux, J.-F. Paiement, P. Vincent and M. Ouimet. In Guyon, I., Gunn, S., Nikravesh, M. and Zadeh, L., editors, Feature Extraction, Foundations and Applications, Springer [chapter(pdf) | chapter(ps.gz) | ref(bibtex)]

The Curse of Highly Variable Functions for Local Kernel Machines (2006), Y. Bengio, O. Delalleau and N. Le Roux. In Advances in Neural Information Processing Systems 18, MIT Press, Cambridge, MA [paper(pdf) | paper(ps.gz) | poster(pdf) | ref(bibtex)]

Convex Neural Networks (2006), Y. Bengio, N. Le Roux, P. Vincent, O. Delalleau and P. Marcotte. In Advances in Neural Information Processing Systems 18, MIT Press, Cambridge, MA [paper(pdf) | paper(ps.gz) | poster(pdf) | ref(bibtex)]

Efficient Non-Parametric Function Induction in Semi-Supervised Learning (2005), O. Delalleau, Y. Bengio and N. Le Roux. In Cowell, R. G. and Ghahramani, Z., editors, Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, Jan 6-8, 2005, Savannah Hotel, Barbados, pages 96-103. Society for Artificial Intelligence and Statistics [paper(pdf) | paper(ps.gz) | ref(bibtex) | poster(pdf)]

Locally Linear Embedding for dimensionality reduction in QSAR (2004), P.-J. L'Heureux, J. Carreau, Y. Bengio, O. Delalleau, and S.Y. Yue. Journal of Computer-Aided Molecular Design, 18:475-482 [paper(pdf) | paper(ps.gz) | ref(bibtex)]

Learning Eigenfunctions Links Spectral Embedding and Kernel PCA (2004), Y. Bengio, O. Delalleau, N. Le Roux, J.-F. Paiement, P. Vincent and M. Ouimet. Neural Computation, 16(10):2197-2219 [paper(pdf) | paper(ps.gz) | ref(bibtex)]

Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering (2004), Y. Bengio, J.-F. Paiement, P. Vincent, O. Delalleau, N. Le Roux and M. Ouimet. In S. Thrun, L. Saul and B. Schölkopf, editors, Advances in Neural Information Processing Systems 16, MIT Press, Cambridge, MA [paper(pdf) | paper(ps.gz) | poster(ps.gz) | ref(bibtex)]

Technical reports, Talks, Posters, ...

Efficient EM Training of Gaussian Mixtures with Missing Data (2012), O. Delalleau, A. Courville and Y. Bengio. arXiv:1209.0521 [paper(pdf) | ref(bibtex)]

Efficient machine learning: theory and practice (Apprentissage machine efficace : théorie et pratique) (2012), O. Delalleau. Ph.D. thesis (French), University of Montreal [thesis(pdf) | presentation(keynote) | ref(bibtex)]

Hierarchical Feature Extraction for Learning from Complex Data in High Dimension (Extraction Hiérarchique de Caractéristiques pour l'Apprentissage à partir de Données Complexes en Haute Dimension) (2008), O. Delalleau. Pre-doctoral report (French), University of Montreal [paper(ps.gz) | paper(pdf) | ref(bibtex)]

Gaussian Mixtures with Missing Data: an Efficient EM Training Algorithm (2008), O. Delalleau, A. Courville and Y. Bengio. Presented at Snowbird 2008, Utah [abstract(pdf) | poster(pdf)]

Justifying and Generalizing Contrastive Divergence (2007), Y. Bengio and O. Delalleau. Technical Report 1311, Département d'Informatique et Recherche Opérationnelle, Université de Montréal [paper(pdf) | ref(bibtex)]

Decision Trees do not Generalize to New Variations (2007), Y. Bengio, O. Delalleau, and C. Simard. Technical Report 1304, Département d'Informatique et Recherche Opérationnelle, Université de Montréal [paper(pdf) | ref(bibtex)]

Learning a Hierarchical Representation of Words within a Neural Language Model (2007), O. Delalleau. IFT6266 class project, Département d'Informatique et Recherche Opérationnelle, Université de Montréal [paper(ps.gz) | paper(pdf) | ref(bibtex)]

Graph-Based Semi-Supervised Learning (2005), O. Delalleau, Y. Bengio and N. Le Roux. Presented at CIAR workshop on manifold learning, Montreal, Canada [slides(pdf)]

The Curse of Dimensionality for Local Kernel Machines (2005), Y. Bengio, O. Delalleau and N. Le Roux. Presented at Snowbird 2005, Utah [slides(pdf) | abstract(pdf) | poster(pdf)]

The Curse of Dimensionality for Local Kernel Machines (2005), Y. Bengio, O. Delalleau, and N. Le Roux. Technical Report 1258, Département d'Informatique et Recherche Opérationnelle, Université de Montréal [paper(ps.gz) | paper(pdf) | ref(bibtex)]

Efficient Non-Parametric Function Induction in Semi-Supervised Learning (2004), Y. Bengio, O. Delalleau, and N. Le Roux. Technical Report 1247, Département d'Informatique et Recherche Opérationnelle, Université de Montréal [paper(ps.gz) | paper(pdf) | ref(bibtex)]

Non-Parametric Function Induction in Semi-Supervised Learning (2004), Y. Bengio, O. Delalleau and N. Le Roux. Presented at Snowbird 2004, Utah [abstract(ps.gz) | poster(ps.gz)]

Spectral Clustering and Kernel PCA are Learning Eigenfunctions (2003), Y. Bengio, P. Vincent, J.-F. Paiement, O. Delalleau, M. Ouimet and N. Le Roux. Technical Report 1239, Département d'Informatique et Recherche Opérationnelle, Université de Montréal [paper(ps.gz) | paper(pdf) | ref(bibtex)]

Out-of-Sample Extensions for Kernel Algorithms (2003), Y. Bengio, O. Delalleau, N. Le Roux, J.-F. Paiement, M. Ouimet and P. Vincent. Presented at MITACS 2003, Montreal [poster(ps.gz)]

Totally unrelated stuff

Check this page.