preprints

1. A.V. Little, M. Maggioni and L. Rosasco,
   Multiscale Geometric Methods for Data Sets I: Intrinsic dimension
2. J. Bouvrie, S. Smale and L. Rosasco,
   Cuts in Hilbert Spaces

2010

• Leibo, J., J. Mutch, L. Rosasco, S. Ullman, and T. Poggio,
  "Invariant Recognition of Objects by Vision"
  CBCL-291Massachusetts Institute of Technology, Cambridge, MA, November 2, 2010


• Smale S., Rosasco L., Bouvrie, J., Caponnetto, A. and Poggio, T.
  "Mathematics of the Neural Response"
  67-91, 2010 10, Foundations of Computational Mathematics.


• G. Chen, A.V. Little, M. Maggioni and L. Rosasco,
  Some Recent Advances in the Geometric Analysis of Point Clouds in High Dimensions
  To appear in 20 Years of Wavelets, 2010


• De Vito, E., Pereverzev S. and Rosasco L.
  "Adaptive Kernel Methods via the Balancing Principle",
  455-479, 2010, Vol. 10, Num. 4, Foundations of Computational Mathematics (also CBCL paper #275/CSAIL #TR-2008-062 MIT 2008).


• De Vito, E., Rosasco, L. and Toigo, A.
  Spectral Regularization for Support Estimation,
  To appear in Advances in Neural Information Processing Systems (NIPS) 23, 2010.


• Mosci, S., Villa, S. and Rosasco, L.
  A primal-dual algorithm for group sparse regularization with overlapping groups.
  To appear in Advances in Neural Information Processing Systems (NIPS) 23, 2010.


• Baldassarre, L., Barla, A., Rosasco, L. and Verri, A.
  Learning Vector Fields via Spectral Filtering.
  To appear in proceeding of ECML 2010.


• Rosasco, L., Mosci, S., Santoro, M., Verri, A. and Villa, S.
  Solving Structured Sparsity Regularization with Proximal Methods.
  To appear in proceeding of ECML 2010.


• Rosasco, L., Mosci, S., Santoro, M., Verri, A. and Villa, S.
  A Regularization Approach to non linear Variable Selection.
  To appear in proceeding of AISTAT 2010.


• Mosci, S., Villa, S. and Rosasco, L.,
  A fast algorithm for structured gene selection.
  Fourth International Workshop on Machine Learning in Systems Biology, 2010.


• Mosci, S., Villa, S. and Rosasco, L.
  Combining l1-l2 regularization with biological prior for multi-level hypoxia signature in Neuroblastoma.
  Fourth International Workshop on Machine Learning in Systems Biology, 2010.

2009

• Bouvrie, J., Rosasco, L. and Poggio, T.
  On Invariance in Hierarchical Models
  Advances in Neural Information Processing Systems (NIPS) 22, 2009.


• Paolo Fardin, Annalisa Barla, Sofia Mosci, Lorenzo Rosasco, Alessandro Verri, Luigi Varesio.
  The l1-l2 regularization framework unmasks the hypoxic signature hidden in the transcriptome of a set of heterogeneous neuroblastoma cell lines.
  BMC Genomics, 2009, 10:474.


• Valerio Del Bono, Alessandra Mularoni, Elisa Furfaro, Emanuele Delfino, Lorenzo Rosasco, Franca Miletich, and Claudio Viscoli
  Clinical Evaluation of a (1,3)-β-D-Glucan Assay for Presumptive Diagnosis of Pneumocystis jiroveci Pneumonia in Immunocompromised Patients
  Clin. Vaccine Immunol. 2009 16: 1524-1526. 


• Rosasco, L., Belkin, M., and De Vito, E.
  "On Learning with Integral Operators"
  Journal of Machine Learning Research,


• N. Noceti, B. Caputo, C. Castellini, L. Baldassarre, A. Barla, L. Rosasco, F. Odone and G. Sandini
  "Towards a theoretical framework for learning multi-modal patterns for embodied agents",
  ICIAP-09-- 15th, International Conference on Image Analysis and Processing. 


• Rosasco, L., Belkin, M., and De Vito, E.
  "A Note on Learning with Integral Operators",
  COLT 2009-- 22nd Annual Conference on Learning Theory.


• Charlie Frogner, Christopher A. Bristow, Tom Morgan, Lorenzo Rosasco, Pouya Kheradpour, Rachel Sealfon, Tomaso Poggio, Manolis Kellis.
  Learning recurrent mRNA expression patterns from systematic analysis of in-situ images of Drosophila embryos.
  (Poster) RECOMB Regulatory and Systems Biology, 2009.


• Wibisono, A., Rosasco, L., and Poggio, T.
  Sufficient Conditions for Uniform Stability of Regularization Algorithms,
  CBCL paper #284/CSAIL Technical Report#MIT-CSAIL-TR-2009-060, Massachusetts Institute of
  Technology, Cambridge, MA, December 1, 2009.

2008

• De Mol, C., De Vito E. and Rosasco L.
  "Elastic Net Regularization in Learning Theory",
  to appear in the Journal of Complexity (also CBCL paper #273/ CSAILTechnical Report #TR-2008-046,
  Massachusetts Institute of Technology, Cambridge, MA, July 24, 2008 and arXiv:0807.3423).


• Lo Gerfo L., Rosasco L., Odone F., De Vito E. and Verri, A.
  "Spectral Algorithms for Supervised Learning",
  Neural Comput. 2008 20: 1873-1897.


• Rosasco L. (joint work with De Mol, C., De Vito E.)
  "Elastic net regularization in learning theory",
  ICML/UAI/COLT 2008 Joint Workshops-- Sparse Optimization and Variable Selection Workshop.


• Rosasco L. (joint work with De Mol, C., De Vito E.)
  "Analysis of Elastic Net Regularization",
  OBERWOLFACH Report, Learning Theory and Approximation Workshop, Mathematisches Forschungsinstitut Oberwolfach.


• S. Mosci, A. Barla, A. Verri and L. Rosasco.
  "Finding Structured Gene Signatures",
  BIBM, 2008-- IEEE International Conference on Bioinformatics and Biomedicine.

2007

• Bauer F., Pereverzev S. and Rosasco L.
  "On Regularization Algorithms in Learning Theory",
  J. Complexity 23(1): 52-72 (2007) (Technical Report DISI-TR-05-19).


• Yao Y., Rosasco L. and Caponnetto, A.
  "On Early Stopping in Gradient Descent Learning",
  Constr. Approx. 26 (2007), no. 2, 289–315.


• Mosci, S., Rosasco, L. and Verri A.
  " Dimensionality reduction and generalization ",
  ICML 2007-- Proceedings of the 24th International Conference on Machine Learning.


• Barla, A., Mosci, S., Rosasco, L. and Verri, A.
  "A method for robust variable selection with significance assessments"
  ESANN-- 16th European Symposium on Artificial Neural Networks, 2007.

2006

• De Vito E., Rosasco L. and Caponnetto, A.
  "Discretization Error Analysis for Tikhonov Regularization ",
  Analysis and Applications Vol. 4, No. 1 (January 2006).

2005

• De Vito E., Rosasco L.,Caponnetto A., De giovannini U. and Odone F.
  "Learning from Examples as an Inverse Problem ",
  Journal of Machine Learning Research 6(May):883--904, 2005.


• De Vito E., Caponnetto A, Rosasco L..
  "Model Selection for Regularized Least-Squares Algorithm in Learning Theory",
  Foundations of Computational Mathematics Volume 5, Number 1 pp. 59 - 85, February 2005.


• Caponnetto A., Rosasco L., Odone F. and Verri A.
  " Support Vectors Algorithms as Regularization Networks ",
  Esann 2005-- 13th European Symposium on Artificial Neural Networks.

2004

• De Vito E., Rosasco L., Caponnetto A., Piana M. and Verri A.
  "Some Properties of Regularized Kernel Methods",
  Journal of Machine Learning Research 5(Oct):1363--1390, 2004. .


• Rosasco L., Caponnetto A., De Vito E., Piana M. and Verri A.
  "Are Loss Function All the Same?"
  Neural Computation, Vol. 16, Issue 5 - May 2004.


• Rosasco L., Caponnetto A., De Vito E., De giovannini U. and Odone F.
  " Learning, Regularization and Ill-posed Inverse problems ",
  NIPS 2004-- Eighteenth Annual Conference on Neural Information Processing Systems.

technical reports

1. Rosasco, L., Belkin, M., and De Vito, E.
   "A Note on Perturbation Results for Learning Empirical Operators"
   CBCL paper #274/ CSAIL Technical Report #TR-2008-052 , Massachusetts Institute of Technology, Cambridge, MA, August 19, 2008.
2. De Vito, E., Pereverzev S. and Rosasco L.
   "Adaptive Kernel Methods via the Balancing Principle",
   CBCL paper #275/CSAIL Technical Report#TR-2008-062 Massachusetts Institute of Technology, Cambridge, MA, October 16, 2008
3. De Mol, C., De Vito E. and Rosasco L.
   "Elastic Net Regularization in Learning Theory",
   CBCL paper #273/ CSAILTechnical Report #TR-2008-046,
   Massachusetts Institute of Technology, Cambridge, MA, July 24, 2008.
   arXiv:0807.3423 (submitted).
4. Rosasco L., De Vito E. and Verri A.
   " Spectral Methods for Regularization in Learning Theory",
   Technical report DISI-TR-05-18.
5. Caponnetto A., Rosasco L., De Vito E. and Verri A.
   "Empirical Effective Dimension and Optimal Rates for Regularized Least Squares Algorithm ",
   CBCL Paper #252/AI Memo #2005-019, MIT, Cambridge, MA, May 2005.
6. Caponnetto A. and Rosasco L.
   " Non Standard Support Vector Machines and Regularization Networks",
   DISI-TR-04-03.
7. De Vito E., Rosasco L., Caponnetto A., Piana M. and Verri A.
   "Representer Theorem for Convex Loss Fuction",
   DISI-TR-03-13.
8. De Vito E., Rosasco L., Caponnetto A., Piana M. and Verri A.
   " Minimization of Tiklhonov Functional: the Continuos Setting",
   DISI-TR-03-14 .