Publications

Below are some of my research papers. If you have questions or comments please feel free to contact me.
An up-to-date list of my publications can be found at Google Scholar here.
Back to home.

2018

• Incremental learning-to-learn with statistical guarantees (with G. Denevi, C. Ciliberto, and D. Stamos) UAI 2018.
• Empirical bounds for functions with weak interactions (with A. Maurer) COLT 2018.
• Empirical risk minimization under fairness constraints (with M. Donini, L. Oneto, S. Ben-David, J. Shawe-Taylor) NeurIPS 2018.

2017

• Reexamining low rank matrix factorization for trace norm regularization (with C. Ciliberto and D. Stamos) arXiv:1706.08934.
• Forward and reverse gradient-based hyperparameter optimization (with L. Franceschi, M. Donini, and P. Frasconi) ICML 2017.
• Sparsity is better with stability: combining accuracy and stability for model selection in brain decoding (with L. Baldassarre and J. Mourao-Miranda) Frontiers in Neuroscience 11(62), 2017.
• Consistent multitask learning with nonlinear output relations (with C. Ciliberto, L. Rosasco, and A. Rudi) NIPS 2017.
• Regret bounds for lifelong learning (with P. Alquier and T. T. Mai) AISTATS 2017.

2016

• Mistake bounds for binary matrix completion (with M. Herbster and S. Pasteris) NIPS 2016.
• Bounds for vector-valued function estimation (with A. Maurer) arXiv:1606.01487.
• Learning with optimal interpolation norms: properties and algorithms (with C. L. Combettes, A. M. McDonald and C. A. Micchelli) arXiv:1603.09273.
• Fitting sparsity and spectral decay with the spectral (k,p)-support norm (with A. M. McDonald and D. Stamos) AISTATS 2016.
• New perspectives on k-support and cluster norms (with A. M. McDonald and D. Stamos) J. Machine Learning Research (to appear).
• The benefit of multitask representation learning (with A. Maurer and B. Romera-Paredes) J. Machine Learning Research 17(81):1-32, 2016.

2015

• Predicting a switching sequence of graph labelings (with M. Herbster and S. Pasteris) J. Machine Learning Research, 16:2003-2022, 2015.
• Learning with dataset bias in latent subcategory models (with D. Stamos, S. Martelli, M. Nabi, A. M. McDonald and V. Murino) CVPR 2015.

2014

• Spectral k-support norm regularization (with A. M. McDonald and D. Stamos) NIPS 2014.
• Large margin local metric learning (with J. Bohne', S. Gentric, Y.Ying) ECCV 2014.
• An inequality with applications to structured sparsity and multitask dictionary learning (with A. Maurer and B. Romera-Paredes) COLT 2014.
• Lower bounds for sparse coding (with A. Maurer and L. Baldassarre) In Measures of Complexity: Festschrift for Alexey Chervonenkis (V. Vovk et al. eds.), 2014.
• New perspectives on k-support and cluster norms (with A. M. McDonald and D. Stamos) arXiv:1403.1481.

2013

• A new convex relaxation for tensor completion (with B. Romera-Paredes) NIPS 2013.
• Regularized robust portfolio estimation (with T. Evgeniou, D. Spinellis, R. Swiderski and N. Nassuphis), 2013.
• Multilinear multitask learning (with B. Romera-Paredes, H. Aung and N. Bianchi-Berthouze) ICML 2013.
• Sparse coding for multitask and transfer learning (with A. Maurer and B. Romera-Paredes) ICML 2013.
• On sparsity inducing regularization methods for machine learning (with A. Argyriou, L. Baldassarre and C. A. Micchelli) In Empirical Inference, Festschrift in Honor of Vladimir N. Vapnik, (B. Scholkopf et al. eds.)
• Excess risk bounds for multitask learning with trace norm regularization (with A. Maurer) COLT 2013.
• Transfer learning to account for idiosyncrasy in face and body expressions (with B. Romera-Paredes, H. Aung, A. C. Williams, P. Watson, N. Bianchi-Berthouze) FG 2013.
• Regularizers for structured sparsity (with C. A. Micchelli and J. M. Morales) Advances in Computational Mathematics 38(3):455-489, 2013.

2012

• Optimal kernel choice for large-scale two-sample tests (with A. Gretton, B. Sriperumbudur, D. Sejdinovic, H. Strathmann, S. Balakrishnan, K. Fukumizu) NIPS 2012.
• Conditional mean embeddings as regressors (with S. Grünewälder, G. Lever, L. Baldassarre, S. Patterson, A. Gretton) ICML 2012.
• Modelling transition dynamics in MDPs with RKHS embeddings (with S. Grünewälder, G. Lever, L. Baldassarre, A. Gretton) ICML 2012.
• Structured sparsity models for brain decoding from fMRI data (with L. Baldassarre and J. Mourao-Miranda) PRNI 2012.
• A tale of many cities: universal patterns in human urban mobility (with A. Noulas, S. Scellato, R. Lambiotte and C. Mascolo) PLoS One 7(5):e37027, 2012.
• Exploiting unrelated tasks in multi-task learning (with B. Romera-Paredes, A. Argyriou and N. Bianchi-Berthouze) AISTATS 2012.
• A general framework for structured sparsity via proximal optimization (with L. Baldassarre, J. M. Morales and A. Argyriou) AISTATS 2012.
• Structured sparsity and generalization (with A. Maurer) J. Machine Learning Research, 13:671-690, 2012.
• PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignements (with D. T. Jones, D. W. A. Buchan and D. Cozzetto) Bioinformatics, 28(2):184-190, 2012.

2011

• Exploiting semantic annotations for clustering geographic areas and users in location-based social networks (with A. Noulas, S. Scellato and C. Mascolo) SMW 2011.
• An empirical study of geographic user activity patterns in foursquare (with A. Noulas, S. Scellato and C. Mascolo) ICWSM 2011.
• Efficient first order methods for linear composite regularizers (with A. Argyriou, C. A. Micchelli, L. Shen and Y. Xu) arXiv:1104.1436.
• Oracle inequalities and optimal inference under group sparsity (with K. Lounici, A. B. Tsybakov and S. van de Geer) Annals of Statistics 39(4):2164-2204, 2011.
• Predictions of hot spot residues at protein-protein interfaces using support vector machines (with S. Lise, D. Buchan and D. T. Jones) PLoS One 6(2):e16774, 2011.

2010

• A family of penalty functions for structured sparsity (with C. A. Micchelli and J. M. Morales) NIPS 2010.
• K-dimensional coding schemes in Hilbert spaces (with A. Maurer) IEEE Transactions on Information Theory, 56(11):5839-5846, 2010.
• On spectral learning (with A. Argyriou and C. A. Micchelli) J. Machine Learning Research, 11:935-953, 2010.

2009

• Prediction of hot spot residues at protein-protein interfaces by combining machine learning and energy-based methods (with S. Lise, C. Archambeau and D. T. Jones) BMC Bioinformatics, 10:365-382, 2009.
• Inferring interests from mobility and social interactions (with A. Noulas, M. Musolesi and C. Mascolo) NIPS Workshop on Analyzing Networks and Learning With Graphs, 2009.
• When is there a representer theorem? Vector versus matrix regularizers (with A. Argyriou and C. A. Micchelli) J. Machine Learning Research, 10:2507-2529, 2009.
• Taking advantage of sparsity in multi-task learning (with K. Lounici, A. B. Tsybakov and S. van de Geer) COLT 2009.
• Empirical Bernstein bounds and sample-variance penalization (with A. Maurer) COLT 2009.
• Entropy conditions for Lr-convergence of empirical processes (with A. Caponnetto and E. De Vito) Advances in Computational Mathematics, 30(4):355-373, 2009.

2008

• Online prediction on large diameter graphs (with M. Herbster and G. Lever) NIPS 2008.
• Fast prediction on a tree (with M. Herbster and S. Rojas-Galeano) NIPS 2008.
• A uniform lower error bound for half-space learning (with A. Maurer) ALT 2008.
• Generalization bounds for K-dimensional coding schemes in Hilbert spaces (with A. Maurer) ALT 2008.
• An algorithm for transfer learning in a heterogeneous environment (with A. Argyriou and A. Maurer) ECML 2008.
• Universal multi-task kernels (with A. Caponnetto, C. A. Micchelli and Y. Ying) J. Machine Learning Research, 9:1615-1646, 2008.
• Convex multi-task feature learning (with A. Argyriou and T. Evgeniou) Machine Learning 73(3):243-272, 2008.
• Online gradient descent learning algorithms (with Y. Ying) Foud. Comp. Math. 8(5):561-596, 2008.

2007

• A spectral regularization framework for multi-task structure learning (with A. Argyriou, C. A. Micchelli and Y. Ying) NIPS 2007.
• A convex optimization approach to modeling heterogeneity in conjoint estimation (with T. Evgeniou and O. Toubia) Marketing Science, 26:805-818, 2007.
• Feature space perspectives for learning the kernel (with C. A. Micchelli) Machine Learning, 66:297-319, 2007.
• Conditional graphical models (with F. Perez-Cruz and Z. Ghahramani) In Predicting Structured Data, edited by G. Bakir et al., MIT Press, 2007.

2006

• Multi-task feature learning (with A. Argyriou and T. Evgeniou) NIPS 2006.
• Prediction on a graph with the perceptron (with M. Herbster) NIPS 2006.
• A DC-programming algorithm for kernel selection (with A. Argyriou, R. Hauser and C. A. Micchelli) ICML 2006.
• Error analysis for online gradient descent algorithms in reproducing kernel Hilbert spaces (with Y. Ying and D.-X. Zhou) Preprint, April 2006.

2005

• Combining graph Laplacians for semi-supervised learning (with A. Argyriou and M. Herbster) NIPS 2005.
• Error bounds for learning the kernel (with C. A. Micchelli, Q. Wu, and D.-X. Zhou) Research Note RN/05/09, Dept of Computer Science, UCL, June, 2005.
• Online learning over graphs (with M. Herbster and L. Wainer) ICML 2005.
• Learning convex combinations of continuously parameterized basic kernels (with A. Argyriou and C. A. Micchelli) COLT 2005.
• Learning the kernel function via regularization (with C. A. Micchelli) J. Machine Learning Research, 6:1099-1125, 2005.
• Learning multiple tasks with kernel methods (with T. Evgeniou and C. A. Micchelli) J. Machine Learning Research, 6:615-637, 2005.
• Wide coverage natural language processing using kernel methods and neural networks for structured data (with F. Costa, P. Frasconi and S. Menchetti) Pattern Recognition Letters, 26(12):1896-1906, 2005.
• On learning vector-valued functions (with C. A. Micchelli) Neural Computation, 17:177-204, 2005.
• Stability of randomized learning algorithms (with A. Elisseeff and T. Evgeniou) J. Machine Learning Research, 6:55-79, 2005 (See also the longer version: Stability of randomized learning algorithms with an application to bootstrap methods).

2004

• Kernels for multi-task learning (with C. A. Micchelli) NIPS 2004.
• Regularized multi-task learning (with T. Evgeniou) SIGKDD 2004
• A function representation for learning in Banach spaces (with C. A. Micchelli) COLT 2004.
• New results on error correcting output codes of kernel machines (with A. Passerini and P. Frasconi) IEEE Trans. on Neural Networks, 15(1):45-54, 2004.
• Leave-one-out error, stability, and generalization of voting combination of classifiers (with A. Elisseeff and T. Evgeniou) Machine Learning, 55(1):71-97, 2004.

2003

• A note on different covering numbers in learning theory. Journal of Complexity, 19:665-671, 2003.
• Leave-one-out error and stability of learning algorithms with applications (with A. Elisseeff) In Advances in Learning Theory: Methods, Models and Applications, NATO Science Series III: Computer and Systems Sciences, Vol. 190, J. Suykens et al. Eds., IOS press, 2003.
• Learning in reproducing kernel Hilbert spaces: a guide tour. Bull. of the Italian Artificial Intelligence Association - AI*IA Notizie, 2003.
• On different ensembles of kernel machines (with M. Yamana, H. Nakahara and S. Amari) ESANN 2003.
• Image representations and feature selection for multimedia database search (with T. Evgeniou, T. Poggio, and C. Papageorgiou) IEEE Trans. on Knowledge and Data Engineering, 15(4):911-920, 2003.
• Combining flat and structured representations for fingerprint classification with recursive neural networks and support vector machines (with Y. Yao, G. Marcialis, P. Frasconi, and F. Roli) Pattern Recognition, 36(2):397-406, 2003.
• Full body person recognition (with C. Nakajima, B. Heisele, and T. Poggio) Pattern Recognition, 36:1997-2006, 2003.

2002

• A simple algorithm for learning stable machines (with S. Andonova, A. Elisseeff and T. Evgeniou) ECAI 2002.
• Regularization and statistical learning theory for data analysis (with T. Evgeniou, T. Poggio and A. Verri) Computational Statistics and Data Analysis, 38:421-432, 2002.
• Support vector machines with clustering for training with very large datasets (with T. Evgeniou) SETN 2002.

2001

• Categorization by learning and combining object parts (with B. Heisele, T. Serre, T. Vetter and T. Poggio) NIPS 2001.
• Component-based face detection (with B. Heisele, T. Serre and T. Poggio) CVPR 2001.
• Fingerprint classification with combination of support vector machines (with Y. Yao and P. Frasconi) AVBPA 2001.

2000

• On the noise model of support vector machine regression (with S. Mukherjee and F. Girosi) ALT 2000.
• Face detection in still gray images (with B. Heisele and T. Poggio) AI Memo 1687, Massachusetts Institute of Technology, May 2000.
• Statistical learning theory: a primer (with T. Evgeniou and T. Poggio) Int. Journal of Computer Vision, 38(1):9-13, 2000.
• Bounds on the generalization performance of kernel machines ensembles (with T. Evgeniou, L. Perez-Breva and T. Poggio) ICML 2000.
• Regularization networks and support vector machines (with T. Evgeniou and T. Poggio) Advances in Computational Mathematics, 13(1):1-50, 2000.
• Feature selection for SVMs (with J. Weston, S. Mukherjee, O. Chapelle, T. Poggio, and V. Vapnik) NIPS 2000.

1999

• From regression to classification in support vector machines (with R. Rifkin and T. Evgeniou) ESANN 1999.
• On the V-gamma dimension for regression in reproducing kernel Hilbert spaces (with T. Evgeniou) ALT 1999.

1998

• Properties of support vector machines (with A. Verri) Neural Computation, 10:955-974, 1998.
• Support vector machines for 3D object recognition (with A. Verri) IEEE Trans. on PAMI, 20(6):637-646, 1998.