Search Machine Learning Repository:
All publications by Massimiliano Pontil
authors venues years



Spectral k-Support Norm Regularization
Andrew M. Mcdonald, Massimiliano Pontil and Dimitris Stamos
Advances in Neural Information Processing Systems 27, 2014


Multilinear Multitask Learning
Bernardino Romera-paredes, Hane Aung, Nadia Bianchi-berthouze and Massimiliano Pontil
Proceedings of the 30th International Conference on Machine Learning (ICML-13), 2013


A New Convex Relaxation for Tensor Completion
Bernardino Romera-paredes and Massimiliano Pontil
Advances in Neural Information Processing Systems 26, 2013


Optimal kernel choice for large-scale two-sample tests
Arthur Gretton, Dino Sejdinovic, Heiko Strathmann, Sivaraman Balakrishnan, Massimiliano Pontil, Kenji Fukumizu and Bharath K. Sriperumbudur
Advances in Neural Information Processing Systems 25, 2012


Conditional mean embeddings as regressors
Guy Lever, Luca Baldassarre, Sam Patterson, Arthur Gretton, Massimiliano Pontil and Steffen Grünewälder
Proceedings of the 29th International Conference on Machine Learning (ICML-12), 2012


Modelling transition dynamics in MDPs with RKHS embeddings
Guy Lever, Luca Baldassarre, Arthur Gretton, Massimiliano Pontil and Steffen Grünewälder
Proceedings of the 29th International Conference on Machine Learning (ICML-12), 2012


Exploiting Unrelated Tasks in Multi-Task Learning
Bernardino Romera-paredes, Andreas Argyriou, Nadia Berthouze and Massimiliano Pontil
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS-12), 2012


A General Framework for Structured Sparsity via Proximal Optimization
Luca Baldassarre, Jean Morales, Andreas Argyriou and Massimiliano Pontil
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS-12), 2012


A Family of Penalty Functions for Structured Sparsity
Jean Morales, Charles A. Micchelli and Massimiliano Pontil
Advances in Neural Information Processing Systems 23, 2010


When Is There a Representer Theorem? Vector Versus Matrix Regularizers
Andreas Argyriou, Charles A. Micchelli and Massimiliano Pontil
Journal of Machine Learning Research, 2009


Universal Multi-Task Kernels
Andrea Caponnetto, Charles A. Micchelli, Massimiliano Pontil and Yiming Ying
Journal of Machine Learning Research, 2008


Online Prediction on Large Diameter Graphs
Mark Herbster, Guy Lever and Massimiliano Pontil
Advances in Neural Information Processing Systems 21, 2008


Fast Prediction on a Tree
Mark Herbster, Massimiliano Pontil and Sergio R. Galeano
Advances in Neural Information Processing Systems 21, 2008


A Spectral Regularization Framework for Multi-Task Structure Learning
Andreas Argyriou, Massimiliano Pontil, Yiming Ying and Charles A. Micchelli
Advances in Neural Information Processing Systems 20, 2007


A DC-programming algorithm for kernel selection
Andreas Argyriou, Raphael Hauser, Charles A. Micchelli and Massimiliano Pontil
Proceedings of the 23th International Conference on Machine Learning (ICML-06), 2006


Prediction on a Graph with a Perceptron
Mark Herbster and Massimiliano Pontil
Advances in Neural Information Processing Systems 19, 2006


Multi-Task Feature Learning
Andreas Argyriou, Theodoros Evgeniou and Massimiliano Pontil
Advances in Neural Information Processing Systems 19, 2006


Online learning over graphs
Mark Herbster, Massimiliano Pontil and Lisa Wainer
Proceedings of the 22nd International Conference on Machine Learning (ICML-05), 2005


Combining Graph Laplacians for Semi--Supervised Learning
Andreas Argyriou, Mark Herbster and Massimiliano Pontil
Advances in Neural Information Processing Systems 18, 2005


Learning the Kernel Function via Regularization
Charles A. Micchelli and Massimiliano Pontil
Journal of Machine Learning Research, 2005


Learning Multiple Tasks with Kernel Methods
Theodoros Evgeniou, Charles A. Micchelli and Massimiliano Pontil
Journal of Machine Learning Research, 2005


Stability of Randomized Learning Algorithms
André Elisseeff, Theodoros Evgeniou and Massimiliano Pontil
Journal of Machine Learning Research, 2005


Kernels for Multi--task Learning
Charles A. Micchelli and Massimiliano Pontil
Advances in Neural Information Processing Systems 17, 2004


Categorization by Learning and Combining Object Parts
Bernd Heisele, Thomas Serre, Massimiliano Pontil, Thomas Vetter and Tomaso Poggio
Advances in Neural Information Processing Systems 14, 2001