Back to list

Massimiliano Pontil Write a Message

Senior Researcher TT (TT2)

Contacts

+39 010 71781 439

About

Massimiliano Pontil received an MSc degree in Physics from the University of Genova in 1994 (summa cum laude) and a PhD in Physics from the same University in 1999. His main research interests are in machine learning, function representation and approximation, numerical optimization, regularization methods, and statistical learning theory. He has made contributions in the areas including kernel methods, multitask and transfer learning, online learning, sparsity regularization, and statistical learning theory. He also studied machine learning applications arising in affective computing, bioinformatics, computer vision, and user modelling, among others. He has published over 30 international journals papers, 10 book chapters and 60 peer reviewed conference proceedings. His research papers have been cited approximately 12,000 times and his h-index is 47 (Google Scholar, March 2016). He was a full time member of academic staff at University College London (UCL) between 2003 and 2015, a Research Associate in the Department of Information Engineering at University of Siena (2001--2002) and a Post-doctoral Fellow at the Massachusetts Institute of Technology (1998--2000). He has been on the programme committee of the main machine learning conferences, including the Annual Conference on Learning Theory (COLT), the International Conference on Machine Learning (ICML), and the Annual Conference on Neural Information Processing Systems (NIPS). He is on the editorial board of the Machine Learning Journal, Statistics and Computing, the Journal of Machine Learning Research, and he is on the Scientific Advisory Board of the Max Planck Institute for Intelligent Systems.

Projects

Research Grants

2010–2014 EPSRC grant EP/H027203/1 entitled “Structured Sparsity Methods in Machine Learning and Convex Optimisation”, Lead PI.

2011–2013 Royal Society International Joint Project 2010/R2, Sole PI.

2009–2011 Consultant for US Air Force grant FA9550-09-1-0511, entitled “Estimation, Approximation and Computation in Learning Theory” (PIs: Profs. C.A. Micchelli and Y. Xu)

2007–2010 BBSRC grant BB/E017452/1 entitled “Prediction of Protein-Protein Interaction Hot Spots using a Combination of Physics and Machine Learning”, £368,821, co-PI (PI: Prof. David Jones, UCL).

2006–2011 EPSRC grant EP/D071542/1 entitled “A New Generation of Trainable Machines for Multi-task Learning”, Sole PI.

2006 EPSRC grant EP/D052807/1 entitled “Study of Regularization Methods in Machine Learning”, Sole PI.

2004–2006 EPSRC grant GR/T18707/017 entitled “Novel Machine Learning Methods Based on Techniques from Approximation, Estimation and Computation”, Sole PI.

2005–2007 IST Programme IST-2002-506778 of the European Community, entitled “Multi-task Learning: Optimization Methods and Applications”, Lead PI.

2003–2005 Senior Participant of US National Science Foundation Grant ITR-0312113, entitled “Adaptive Kernel Based Machine Learning Methods” (PIs: Profs. Y. Xu and C.A. Micchelli).

2002 Italian Ministry of Education, University and Research (MIUR) Project “Giovani Ricercatori” entitled “Feature Selection with Kernel Machines Techniques”.

 

Advisory Boards

2013 Evaluation Committee, Ecole Normale Superieure de Cachan, France.

2012–2017 Scientific Advisory Board, Max Planck Institute for Biological Cybernetics, Germany.

 

Editorial Board

2013– Journal of Machine Learning Research, Action Editor.

2013– Statistics and Computing.

2009– Machine Learning Journal.

2004–2006 Pattern Recognition Letters.

 

Invited talks

Over 40 Invited conference presentations and 50 invited seminars/lectures/colloquia at Universities and Research Institutes.

 

Program Committees

2016 International Conference on Machine Learning (ICML), Area Chair.

2016 International Conference on Pattern Recognition Applications and Methods (ICPRAM).

2015 Neural Information Processing Systems (NIPS), Area Chair.

2015 International Conference on Machine Learning (ICML), Area Chair.

2015 Annual Conference on Learning Theory (COLT).

2014 International Conference on Machine Learning (ICML), Area Chair.

2013 Neural Information Processing Systems (NIPS), Area Chair.

2013 International Workshop on Similarity-Based Pattern Analysis and Recognition (SIMBAD).

2012 International Conference on Artificial Intelligence and Statistics (AISTATS), Area Chair.

2011 Annual Conference on Learning Theory (COLT).

2011 International Workshop on Similarity-Based Pattern Analysis and Recognition (SIMBAD).

2010 Annual Conference on Learning Theory (COLT).

2010 Eighth International Workshop on Mining and Learning with Graphs (MLG-2010).

2009 NIPS Workshop on Transfer Learning for Structured Data.

2009 International Conference on Algorithmic Learning Theory Conference (ALT).

2009 International Conference on Machine Learning (ICML), Area Chair.

2008 Annual Conference on Learning Theory (COLT).

2007 European Conference on Machine Learning (ECML).

2006 Annual Conference on Learning Theory (COLT).

2006 Joint IAPR International Workshops on Structural and Syntactic Pattern Recognition and Statistical Techniques in Pattern Recognition.

2005 Annual Conference on Learning Theory (COLT).

2004 International Conference on Machine Learning (ICML).

 

Organization

2015 Co-organizer, Dagstuhl Seminar 15152, entitled ”Machine Learning with Interdependent and Non-identically Distributed Data, Dagstuhl, Germany.

2012 Co-organizer, ICML Workshop entitled “Object, Functional and Structured Data: Towards Next Generation Kernel-Based Methods”, Edinburgh, Scotland.

2010 Co-organizer, Conference entitled “Information Representation and Estimation”, UCL, UK.

2009 Co-organizer, Workshop entitled “Sparsity in Machine Learning and Statistics”, Cumberland Lodge, UK.

2006 Co-organizer, Open House on “Multi-Task and Complex Outputs Learning”, UCL, UK.

2005 Co-chair, NIPS Workshop entitled “Inductive Transfer: 10 Year Later”, British Columbia, Canada.

2005 Co-chair, NIPS Workshop entitled “Accuracy-Regularization Frontier”, British Columbia, Canada.

2003 Session Co-organizer, European Symposium of Artificial Neural Networks (ESANN), Bruges, Belgium.

1999 Co-organizer, Workshop entitled “Support Vector Machines: Theory and Applications”, Crete, Greece.

 

Teaching Activity

Dept of Computer Science, UCL:

Graduate and 3rd year course entitled “Supervised Learning”, Fall 2010–2014.

Graduate and 3rd year course entitled “Mathematical Methods for Machine Learning”, Fall 2009–2014.

Graduate and 4th year course entitled “Advanced Topics in Machine Learning”, Spring 2010 and 2011.

Graduate and 4th year course entitled “Advanced Topics in Machine Learning”, Spring 2005 and 2006.

Graduate and 3rd year course entitled “Supervised Learning”, Fall 2005.

MScCS course entitled “Fundamentals of Mathematics”, Fall 2005 (10 lectures).

Graduate and 3rd year course entitled “Information Theory”, Fall 2003 and 2004.

Elsewhere:

Master Course entitled “Advanced Machine Learning”, Ecole Polytechnique, University Paris-Saclay, March 2015 (12 lectures).

PhD course entitled “Kernel-based Methods” University Carlos III of Madrid, September 2002 (12 lectures).

PhD course entitled “Elements of Statistical Learning”, University of Florence, Spring 2002 (20 lectures).

3rd year course entitled “Introduction to Machine Learning”, University of Siena, Spring 2002 (24 lectures).

PhD course entitled “Statistical Learning Theory”, City University of Hong Kong, February 2002 (10 lectures).

1st year course entitled “Fundamentals of Computer Science”, Univ. of Florence, Fall 2001 (40 lectures).

Selected Publications

Journal Articles

A. Maurer, B. Romera-Paredes, M. Pontil (Forthcoming) The benefit of multitask representation learning. Journal of Machine Learning Research (to appear).

McDonald, A.M., Pontil, M., Stamos, D. (Forthcoming). New perspectives on k-support and cluster norms. Journal of Machine Learning Research.

M. Herbster, S. Pasteris, M. Pontil. Predicting a switching sequence of graph labelings. J. Machine Learning Research, 16:2003–2022, 2015.

Montoya-Martinez, J., Art´es-Rodriguez, A., Pontil, M., Hansen, L.K. (2014). A regularized matrix factorization approach to induce structured sparse-low-rank solutions in the EEG inverse problem. EURASIP Journal on Advances in Signal Processing, 1:1-13.

Micchelli, C.A., Morales, J.M., Pontil, M. (2013). Regularizers for structured sparsity. Advances in Computational Mathematics, 38(3):455-489.

Noulas, A., Scellato, S., Lambiotte, R., Pontil, M., Mascolo, C. (2012). A tale of many cities: universal patterns in human urban mobility. PLoS One, 7(5):e37027.

Maurer, M. and Pontil, M. (2012). Structured sparsity and generalization. Journal of Machine Learning Research, 13:671-690.

Jones, D.T., Buchan, D.W.A., Cozzetto, D., Pontil, M. (2012). PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments. Bioinformatics, 28(2):184-190.

Lounici, K., Pontil, M., Tsybakov, A.B., van de Geer, S. (2011). Oracle inequalities and optimal inference under group sparsity. Annals of Statistics, 39(4):2164-2204.

Lise, S., Buchan, D., Pontil, M., Jones, D.T. (2011) Predictions of hot spot residues at protein-protein interfaces using support vector machines. PLoS One, 6(2):e16774.

Maurer, A. and Pontil, M. (2010). K-dimensional coding schemes in Hilbert spaces. IEEE Transactions on Information Theory, 56(11):5839-5846.

Argyriou, A., Micchelli, C.A., Pontil, M. (2010). On spectral learning. Journal of Machine Learning Research, 11:935-953.

Lise, L., Archambeau, C., Pontil, M., Jones, D.T. (2009). Prediction of hot spot residues at protein-protein interfaces by combining machine learning and energy-based methods. BMC Bioinformatics, 10:365-382.

Argyriou, A., Micchelli, C.A., Pontil, M. (2009). When is there a representer theorem? Vector versus matrix regularizers. Journal of Machine Learning Research, 10:2507-2529.

Caponnetto, A., De Vito, E., Pontil, M. (2009). Entropy conditions for Lr-convergence of empirical processes. Advances in Computational Mathematics, 30(4):355-373.

Argyriou, A., Evgeniou, T., Pontil,M. (2008). Convex multi-task feature learning. Machine Learning, 73(3):243-272.

Caponnetto, A., Micchelli, C.A., Pontil, M., Ying, Y. (2008). Universal multi-task kernels. Journal of Machine Learning Research, 9:1615-1646.

Ying, Y. and Pontil, M. (2008). Online gradient descent learning algorithms. Foundations of Computational Mathematics, 8(5):561-596.

Evgeniou, T., Pontil, M., Toubia, O. (2007). A convex optimization approach to modeling heterogeneity in conjoint estimation. Marketing Science, 26:805-818.

Micchelli, C.A. and Pontil, M. (2007). Feature space perspectives for learning the kernel. Machine Learning, 66:297-319.

Costa, F., Frasconi, P., Menchetti, S., Pontil, M. (2005). Wide coverage natural language processing using kernel methods and neural networks for structured data. Pattern Recognition Letters, 26(12):1896-1906.

Elisseeff, A., Evgeniou, T., Pontil, M. (2005). Stability of randomized learning algorithms. Journal of Machine Learning Research, 6:55-79.

Evgeniou, T., Micchelli, C.A., Pontil, M. (2005). Learning multiple tasks with kernel methods. Journal of Machine Learning Research, 6:615-637.

Micchelli, C.A. and Pontil, M. (2005). Learning the kernel function via regularization. Journal of Machine Learning Research, 6:1099-1125.

Micchelli, C.A. and Pontil, M. (2005). On learning vector-valued functions. Neural Computation, 17(1):177-204.

Evgeniou, T., Pontil, M., Elisseeff, A. (2004). Leave-one-out error, stability, and generalization of voting combination of classifiers. Machine Learning, 55(1):71-97.

Passerini, A., Pontil, M., Frasconi, P. (2004). New results on error correcting output codes of kernel machines. IEEE Trans. on Neural Networks, 15(1):45-54.

Nakajima, C., Pontil, M., Heisele, B., Poggio, T. (2003). Full body person recognition. Pattern Recognition, 36:1997-2006.

Evgeniou, T., Pontil, M., Poggio, T., Papageorgiou, C. (2003). Image representations and feature selection for multimedia database search. IEEE Trans. on Knowledge and Data Engineering, 15(4):911-920.

Pontil, M. (2003). A note on different covering numbers in learning theory. Journal of Complexity, 19:665-671.

Yao, Y., Marcialis, G., Pontil, M., Frasconi, P., Roli, F. (2003). Combining flat and structured representations for fingerprint classification with recursive neural networks and support vector machines. Pattern Recognition, 36(2):397-406.

Evgeniou, T., Poggio, T., Pontil, M., Verri, A. (2002). Regularization and statistical learning theory for data analysis. Computational Statistics and Data Analysis, 38:421-432.

Evgeniou, T., Pontil, M., Poggio, T. (2000). Regularization networks and support vector machines. Advances in Computational Mathematics, 13(1):1-50.

Evgeniou, T., Pontil, M., Poggio, T. (2000). Statistical learning theory: a primer. International Journal of Computer Vision, 38(1):9-13.

Pallavicini, M., Patrignani, C., Pontil, M., Verri, A. (1998). Electron identification with k-nearest-neighbor techniques. Nucl. Inst. and Meth. in Phys. Res. A, 405:133-138.

Pontil, M. and Verri, A. (1998). Properties of support vector machines. Neural Computation, 10:955-974.

Pontil, M. and Verri, A. (1998). Support vector machines for 3D object recognition. IEEE Trans. Pattern Anal. Mach. Intell., 20(6):637-646.

 

Book Chapters

Maurer, A., Pontil, M., Baldassarre, L. Lower bounds for sparse coding. In Measures of Complexity, Vovk, V., Papadopoulos, H., Gammerm, A. (eds), Springer.

Evgeniou, T., Pontil, M., Spinellis, D., Swiderski, R., Nassuphis, N. (2014). Regularized robust portfolio estimation. In Regularization, Optimization, Kernels, and Support Vector Machines, Suykens, J.A.K., Signoretto, M., Argyriou, A. (eds), Chapman & Hall.

Argyriou, A., Baldassarre, L., Micchelli, C.A., Pontil, M. (2013). On sparsity inducing regularization methods for machine learning. In Empirical Inference – Festschrift in Honor of Vladimir N. Vapnik, Schoelkopf, B., Luo, Z., Vovk, V. (eds), Springer.

Odone, F., Pontil, M., Verri, A. (2009). Machine learning techniques for biometrics. In Handbook of Remote Biometrics for Surveillance and Security, Tistarelli, M., Li, S.Z., Chellappa, R. (eds.) Springer, 247-271.

Perez-Cruz, F., Ghahramani, Z., Pontil, M. (2007). Conditional graphical models. In Predicting Structured Data, Bakir, G., Hofmann, T., Sch¨olkopf, B., Smola, A.J., Taskar, B., Vishwanathan, S. (eds.) MIT Press, 265-281.

Eliseeff, A., Pontil, M. (2003). Leave-one-out error and stability of learning algorithms with applications. In Advances in Learning Theory: Methods, Models and Applications, NATO Science Series III: Computer and Systems Sciences, Suykens, J.A.K.,Horvath, I., Basu, S., Micchelli, C.A., Vandewalle, J. (eds.) IOS Press, 190:111-124.

Evgeniou, T. and Pontil, M. (2001). Support vector machines: theory and applications. In Machine Learning and Its Applications Paliouras, G.,Karkaletsis, V., Spyropoulos, C.D. (ed.) Springer, 249-257.

Evgeniou, T., Pontil, M., Poggio, T. (1999). A unified framework for regularization networks and support vector machines. In Advances in Large Margin Classifiers, Smola, A.J., Bartlett, P. Sch¨olkopf, B. Schurmans, D. (eds.) MIT Press, 171-204.

Pontil, M., Rogai,S., Verri, A. (1998). Support vector machines: a large scale QP. In High Performance Algorithms and Software in Nonlinear Optimization, De Leone, R., Murli, A., Pardalos, P.M., Toraldo, G. (eds.) Kluwer Academic Publishers, 315-336.

 

Conferences (refereed)

McDonald, A.M., Pontil, M., Stamos, D. (2016) Fitting sparsity and spectral decay with the spectral (k,p)-support norm. Proc. 19th International Conference on Artificial Intelligence and Statistics (AISTATS).

Stamos, D., Martelli, S., Nabi, M., McDonald, A., Murino, V., Pontil, M. (2015). Learning with dataset bias in latent subcategory models. Conference on Computer Vision and Pattern Recognition (CVPR).

McDonald, A.M., Pontil, M., Stamos, D. (2014). New perspectives on k-support and cluster norms. Advances in Neural Information Processing Systems (NIPS), 27.

Bohne', J., Ying, Y., Pontil, M. (2014) Large Margin Local Metric Learning. European Conference on Computer Vision (ECCV), pages 679-694.

Maurer, M., Pontil, M., Romera-Paredes, B. (2014). An inequality with applications to structured sparsity and multitask dictionary learning. 27th Annual Conference on Learning Theory (COLT).

Romera-Paredes, B. and Pontil, M. (2013). A new convex relaxation for tensor completion. Advances in Neural Information Processing Systems (NIPS), 26, pages 2967–2975.

Romera-Paredes, B., Aung, M.S.H., Bianchi-Berthouze, N., Pontil, M. (2013). Multilinear multitask learning. 30th International Conference on Machine Learning (ICML), JMLR W&CP 28(2)343-351.

Maurer, A. and Pontil, M. (2013). Excess risk bounds for multitask learning with trace norm regularization. 26th Annual Conference on Learning Theory (COLT).

Maurer, A., Pontil, M., Romera-Paredes, B. (2013). Sparse coding for multitask and transfer learning. 30th International Conference on Machine Learning (ICML), JMLR W&CP 28(2):343-351.

Romera-Paredes, B., Aung, M.S.H., Pontil, M., Williams, A., Watson, P., Bianchi-Berthouze, N. (2013). Transfer learning to account for idiosyncrasy in face and body expressions. 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), pages 1-6.

Gretton, A., Sriperumbudur, B., Sejdinovic, D., Strathmann, H., Balakrishnan, S., Pontil, M., Fukumizu, K. (2012). Optimal kernel choice for large-scale two-sample tests. Advances in Neural Information Processing Systems (NIPS), 25, 1214-1222.

Gruunewalder, S., Lever, G., Baldassarre, L., Patterson, S., Gretton, A., Pontil, M. (2012). Conditional mean embeddings as regressors. 29th International Conference on Machine Learning (ICML).

Grunnewalder, S., Lever, G., Baldassarre, L., Pontil, M., Gretton, A. (2012). Modelling transition dynamics in MDPs with RKHS embeddings. Proc. 29th International Conference on Machine Learning (ICML).

Baldassarre, L., Morales, J.M., Pontil, M. (2012). Incorporating Additional Constraints in Sparse Estimation. 16th IFAC Symposium on System Identification (SYSID).

Baldassarre, L., Morales, J.M., Argyriou, A. Pontil, M. (2012). A General Framework for Structured Sparsity via Proximal Optimization. Proc. 15th International Conference on Artificial Intelligence and Statistics (AISTATS).

Romera-Parades, B., Argyriou, A., Bianchi-Berthouze, N. Pontil, M. (2012). Exploiting Unrelated Tasks in Multi-Task Learning. 15th International Conference on Artificial Intelligence and Statistics (AISTATS).

Noulas, A. Scellato, S., Mascolo, C., Pontil, M. (2011). An Empirical Study of Geographic User Activity Patterns in Foursquare. 5th International AAAI Conference on Weblogs and Social Media (ICWSM 2011).

Micchelli, C.A., Morales, J.M., Pontil, M. (2010). A family of penalty functions for structured sparsity. Advances in Neural Information Processing Systems (NIPS), 23, 1612-1623.

Herbster, M., Lever, G., Pontil, M. (2009). Online prediction on large diameter graphs. Advances in Neural Information Processing Systems (NIPS) 21, 649-656.

Herbster, M., Pontil, M., Rojas-Galeano, S. (2009). Fast prediction on a tree. Advances in Neural Information Processing Systems (NIPS) 21, 657-664.

Lounici, K., Pontil, M., Tsybakov, A.B., van de Geer, S.A. (2009). Taking advantage of sparsity in multitask learning. 22nd Annual Conference on Learning Theory (COLT), 73-82.

Maurer, A. and Pontil, M. (2009). Empirical Bernstein bounds and sample-variance penalization. 22nd Annual Conference on Learning Theory (COLT), 115-124.

Argyriou, A., Maurer, A., Pontil, M. (2008). An algorithm for transfer learning in a heterogeneous environment. European Conference on Machine Learning (ECML), 71-85.

Maurer, A. and Pontil, M. (2008). A uniform lower error bound for half-space learning. Algorithmic Learning Theory (ALT), 19th International Conference, 70-78.

Maurer, A. and Pontil, M. (2008). Generalization bounds for k-dimensional coding schemes in Hilbert spaces. Algorithmic Learning Theory (ALT), 19th International Conference, 79-91.

Argyriou, A., Evgeniou, T., Pontil, M. (2007). Multi-task feature learning. Advances in Neural Information Processing (NIPS), 19, 41-48.

Argyriou, A., Micchelli, C.A., Pontil, M., Ying, Y. (2007). A spectral regularization framework for multitask structure learning. Advances in Neural Information Processing Systems (NIPS), 20, 25-32.

Herbster, M. and Pontil, M. (2007). Prediction on a graph with the perceptron. Advances in Neural Information Processing Systems (NIPS), 19, 41-48.

Argyriou, A., Hauser, R., Micchelli, C.A., Pontil, M. (2006). A DC-programming algorithm for kernel selection. 23rd International Conference on Machine Learning (ICML), 41-48.

Argyriou, A., Herbster, M., Pontil, M. (2006). Combining graph laplacians for semi-supervised learning. Avances in Neural Information Processing Systems (NIPS), 18, 67-74.

Argyriou, A., Micchelli, C.A., Pontil, M. (2005). Learning convex combinations of continuously parameterized basic kernels. 18th Annual Conference on Learning Theory (COLT), 338-352.

Herbster, M., Pontil, M., Wainer, L. (2005). Online learning over graphs. 22nd International Conference on Machine Learning (ICML), 305-312.

Micchelli, C.A., Pontil, M. (2005). Kernels for multi-task learning. Advances in Neural Information Processing Systems (NIPS), 17, 921-928.

Evegniou, T. and Pontil, M. (2004). Regularized multi-task learning. 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 109-117.

Micchelli, C.A. and Pontil, M. (2004). A function representation for learning in Banach spaces. 17th Annual Conference on Learning Theory (COLT), 255-269.

Pontil, M. (2003). An introduction to learning with reproducing kernel Hilbert spaces. 11th IFAC Symposium on System Identification, 783-788.

Yamana, M., Nakahara, H., Pontil, M., Amari, S. (2003). On different ensembles of kernel machines. 11th European Symposium on Artificial Neural Networks (ESANN), 197-201.

Andonova, S., Elisseeff, A., Evgeniou, T., Pontil, M. (2002). A simple algorithm for learning stable machines. 15th Eureopean Conference on Artificial Intelligence (ECAI), 513-517.

Evgeniou, T. and Pontil, M. (2002). Support vector machines with clustering for training with very large datasets. Second Hellenic Conference on AI, 346-354.

Passerini, A., Pontil, M., Frasconi, P. (2002). From margins to probabilities in multiclass learning problems. 15th Eureopean Conference on Artificial Intelligence (ECAI), 400-404.

Heisele, B., Serre, T., Pontil, M., Poggio, T. (2001). Component-based face detection. Conference on Computer Vision and Pattern Recognition (CVPR), 657-662.

Heisele, B., Serre, T., Pontil, M., Vetter, T., Poggio, T. (2001). Categorization by learning and combining object parts. Advances in Neural Information Processing Systems (NIPS), 14, 1239-1245.

Yao, Y., Marcialis, G., Pontil, M., Frasconi, P., and Roli, F. (2001). A New Machine Learning Approach to Fingerprint Classification. 7th Congress of the Italian Association for Artificial Intelligence, 57-63.

Yao, Y., Frasconi, P., and Pontil, M. (2001). Fingerprint Classification with Combinations of Support Vector Machines. 3rd Int. Conf. on Audio- and Video-Based Biometric Person Authentication, 253-258.

Evgeniou, T., Pontil, M., Papageorgiou, C., Poggio, T. (2000). Image representations for object detection using kernel classifiers. 2nd Asian Conf. on Computer Vision (ACCV), 687-692.

Evgeniou, T., Perez-Breva, L., Pontil, M., Poggio, T. (2000). Bounds on the generalization performance of kernel machine ensembles. 17th International Conference on Machine Learning (ICML), 271-278.

Evgeniou, T. and Pontil, M. (2000). A note on the generalization performance of kernel classifiers with margin. Algorithmic Learning Theory (ALT) 306-315.

Nakajima, C., Itoh, N., Pontil, M., Poggio, T. (2000). Object recognition and detection by a combination of support vector machine and rotation invariant phase only correlation. International Conference on Pattern Recognition (ICPR), 4787-4790.

Nakajima, C., Pontil, M., Poggio,T . (2000). People recognition and pose estimation in image sequences. International Joint Conference on Neural Networks (IJCNN), 4:189-196.

Pontil, M., Mukherjee, S., Girosi, F. (2000). On the noise model of support vector machines regression. Algorithmic Learning Theory (ALT), 316-324.

Campbell, C., Evgeniou, T., Heisele, B., Pontil, M. (2000). Machine learning strategies for complex tasks. Proceedings of 1st IEEE-RAS International Conference on Humanoid Robots.

Weston, J., Mukherjee, S., Chapelle, O., Pontil, M., Poggio, T., Vapnik, V.N. (2000). Feature selection for SVMs. Advances in Neural Information Processing Systems (NIPS), 13, 668-674.

Barabino, N., Pallavicini, M., Petrolini, A., Pontil, M. Verri, A. (1999). Support vector machines vs multi-layer perceptrons in particle identification. 7th European Symposium on Artificial Neural Networks (ESANN), 257-262.

Evgeniou, T. and Pontil, M. (1999). On the V-gamma dimension for regression in reproducing kernel Hilbert spaces. 10th International Conference on Algorithmic Learning Theory (ALT), 106-117.

Pontil, M., Rifkin, R.M., Evgeniou, T. (1999). From regression to classification in support vector machines. 7th European Symposium on Artificial Neural Networks (ESANN), 225-230.

Rifkin, R.M., Pontil, M., Verri, A. (1999). A note on support vector machine degeneracy. 10th International Conference on Algorithmic Learning Theory (ALT), 252-263.

Pontil, M., Rogai, S., Verri, A. (1998). Recognizing 3D objects with linear support vector machines. 5th European Conference on Computer Vision (ECCV), 469-483.

Pontil, M. and Verri, A. (1997). Direct aspect-based 3D object recognition. 9th International Conference on Image Analysis and Processing (ICIAP), 300-307.

 

Workshops (refereed)

Montoya-Martınez, J., Artes-Rodrıguez, A., Pontil, M. (2014). Structured sparse-low rank matrix factorization

for the EEG inverse problem. Proceedings of the 4th InternationalWorkshop on Cognitive Information

Processing (CIP), 1-6.

Martınez-Rego, D. and Pontil, M. (2013) Multi-task averaging via task clustering. 2nd InternationalWorkshop

on Similarity-Based Pattern Analysis (SIMBAD 2013), 148-159.

Baldassarre, L. Mourao-Miranda, J. Pontil, M. (2012). Structured sparsity models for brain decoding from fMRI data. Pattern Recognition in NeuroImaging (PRNI 2012).

Maurer, A. and Pontil, M. (2012). Transfer learning in a heterogeneous environment. Proceedings of the 3rd Workshop on Cognitive Information Processing (CIP 2012).

Montoya-Martinez, J., Arte´s-Rodriguez, A., Hansen, L.K., Pontil, M. (2012). Structured sparsity regularization approach to the EEG inverse problems. Proceedings of the 3rd Workshop on Cognitive Information Processing (CIP 2012).

Romera-Paredes, B., Pontil, M., Bianchi-Berthouze, N. (2011). Leveraging different transfer learning assumptions: shared features, hierarchical and semi-supervised. NIPSWorkshop on Challenges in Learning Hierarchical Models: Transfer Learning and Optimization.

Noulas, A. Scellato, S., Mascolo, C., Pontil, M. (2011). Exploiting semantic annotations for clustering geographic areas and users in location-based social networks. Proceedings of 3rd Workshop Social Mobile Web (SMW11).

Noulas, A., Musolesi, M., Pontil, M., Mascolo, C. (2009). Inferring interests from mobility and social interactions. NIPS Workshop on Analyzing Networks and Learning With Graphs.

Menchetti, S., Costa, F., Frasconi, P., Pontil, M. (2003). Comparing convolution kernels and recursive neural networks for learning preferences on structured data. Proc. Artificial Neural Networks in Pattern Recognition (ANNPR).

Martinez, D., Donini, M., Shawe-Taylor J., Pontil, M. (2015). Multitask classification on Big Data via ADMM. Dept of Computer Science, University College London.

Signoretto, M., Langone, R., Pontil, M., Suykens, J. (2014). Graph based regularization for multilinear multitask learning. ESAT-STADIUS Technical Report, Katholieke Universiteit Leuven.

Argyriou, A., Micchelli, C.A., Pontil, M., Shen, L., Xu, Y. (2011). Efficient first order methods for linear composite regularizers. arXiv:1106.5236

Pontil, M., Ying, Y., Zhou, D.X. (2006). Error analysis for online gradient descent algorithms in reproducing kernel Hilbert spaces.

Micchelli, C.A., Pontil, M., Wu, Q., Zhou, D.X. (2005). Error bounds for learning the kernel. Research Note RN/05/09 Department of computer Science, UCL.

Heisele, B., Poggio, T., Pontil, M. (2000). Face detection in still gray images. CBCL Paper #187/AI Memo #1687, Massachusetts Institute of Technology.

 

Awards

Best Paper Runner Up, 2013 International Conference on Machine Learning, Atlanta, USA.

Scientific Advisory Board, Max Planck Institute for Intelligent Systems, Germany, 2012-2017.

EPSRC Advanced Research Fellowship, UK, 2006–2011.

Edoardo R. Caianiello Award for the Best Italian PhD Thesis on Connectionism, Italy, 2002.

INFORMATION NOTICE ON COOKIES

IIT's website uses the following types of cookies: browsing/session, analytics, functional and third party cookies. Users can choose whether or not to accept the use of cookies and access the website.
By clicking on further information, the full information notice on the types of cookies used will be displayed and you will be able to choose whether or not to accept cookies whilst browsing on the website.
Further information
Accept and close

I numeri di IIT

L’Istituto Italiano di Tecnologia (IIT) è una fondazione di diritto privato - cfr. determinazione Corte dei Conti 23/2015 “IIT è una fondazione da inquadrare fra gli organismi di diritto pubblico con la scelta di un modello di organizzazione di diritto privato per rispondere all’esigenza di assicurare procedure più snelle nella selezione non solo nell’ambito nazionale dei collaboratori, scienziati e ricercatori ”.

IIT è sotto la vigilanza del Ministero dell'Istruzione, dell'Università e della Ricerca e del Ministero dell'Economia e delle Finanze ed è stato istituito con la Legge 326/2003. La Fondazione ha l'obiettivo di promuovere l'eccellenza nella ricerca di base e in quella applicata e di favorire lo sviluppo del sistema economico nazionale. La costruzione dei laboratori iniziata nel 2006 si è conclusa nel 2009.

Lo staff complessivo di IIT conta circa 1440 persone. L’area scientifica è rappresentata da circa l’85% del personale. Il 45% dei ricercatori proviene dall’estero: di questi, il 29% è costituito da stranieri provenienti da oltre 50 Paesi e il 16% da italiani rientrati. Oggi il personale scientifico è composto da circa 60 principal investigators, circa 110 ricercatori e tecnologi di staff, circa 350 post doc, circa 500 studenti di dottorato e borsisti, circa 130 tecnici. Oltre 330 posti su 1400 creati su fondi esterni. Età media 34 anni. 41% donne / 59 % uomini.

Nel 2015 IIT ha ricevuto finanziamenti pubblici per circa 96 milioni di euro (80% del budget), conseguendo fondi esterni per 22 milioni di euro (20% budget) provenienti da 18 progetti europei17 finanziamenti da istituzioni nazionali e internazionali, circa 60 progetti industriali

La produzione di IIT ad oggi vanta circa 6990 pubblicazioni, oltre 130 finanziamenti Europei e 11 ERC, più di 350 domande di brevetto attive, oltre 12 start up costituite e altrettante in fase di lancio. Dal 2009 l’attività scientifica è stata ulteriormente rafforzata con la creazione di dieci centri di ricerca nel territorio nazionale (a Torino, Milano, Trento, Parma, Roma, Pisa, Napoli, Lecce, Ferrara) e internazionale (MIT ed Harvard negli USA) che, unitamente al Laboratorio Centrale di Genova, sviluppano i programmi di ricerca del piano scientifico 2015-2017.

IIT: the numbers

Istituto Italiano di Tecnologia (IIT) is a public research institute that adopts the organizational model of a private law foundation. IIT is overseen by Ministero dell'Istruzione, dell'Università e della Ricerca and Ministero dell'Economia e delle Finanze (the Italian Ministries of Education, Economy and Finance).  The Institute was set up according to Italian law 326/2003 with the objective of promoting excellence in basic and applied research andfostering Italy’s economic development. Construction of the Laboratories started in 2006 and finished in 2009.

IIT has an overall staff of about 1,440 people. The scientific staff covers about 85% of the total. Out of 45% of researchers coming from abroad 29% are foreigners coming from more than 50 countries and 16% are returned Italians. The scientific staff currently consists of approximately 60 Principal Investigators110 researchers and technologists350 post-docs and 500 PhD students and grant holders and 130 technicians. External funding has allowed the creation of more than 330 positions . The average age is 34 and the gender balance proportion  is 41% female against 59% male.

In 2015 IIT received 96 million euros in public funding (accounting for 80% of its budget) and obtained 22 million euros in external funding (accounting for 20% of its budget). External funding comes from 18 European Projects, other 17 national and international competitive projects and approximately 60 industrial projects.

So far IIT accounts for: about 6990 publications, more than 130 European grants and 11 ERC grants, more than 350 patents or patent applications12 up start-ups and as many  which are about to be launched. The Institute’s scientific activity has been further strengthened since 2009 with the establishment of 11 research nodes throughout Italy (Torino, Milano, Trento, Parma, Roma, Pisa, Napoli, Lecce, Ferrara) and abroad (MIT and Harvard University, USA), which, along with the Genoa-based Central Lab, implement the research programs included in the 2015-2017 Strategic Plan.