Pubblications

Recent Technical Reports (back)

  1. Emilia Magnani, Ernesto De Vito, Philipp Hennig, Lorenzo Rosasco
    Learning convolution operators on compact abelian groups [pdf]
    Technical Report arXiv:2501.05279
  2. Giovanni S. Alberti, Ernesto De Vito, Tapio Helin, Matti Lassas, Luca Ratti, Matteo Santacesaria
    Learning sparsity-promoting regularizers for linear inverse problems [pdf]
    Technical Report arXiv:2412.16031
  3. Antoine Chatalic, Nicolas Schreuder, Ernesto De Vito, and Lorenzo Rosasco
    Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling [pdf]
    Technical Report arXiv:2311.13548
  4. Nicolò Pagliana, Alessandro Rudi, Ernesto De Vito, Lorenzo Rosasco
    Interpolation and Learning with Scale Dependent Kernels [pdf]
    Technical Report arXiv:2006.09984
Journal Papers (back)

  1. Andrea Della Vecchia, Ernesto De vito, Jaouad Mourtada, and Lorenzo Rosasco
    The Nyström method for convex loss functions [pdf]
    Journal Machine Learing Research 25 (360) 1-60 (2024)
  2. Jonathan C. Rodriguez, Ernesto De Vito, Cesare Molinari, Lorenzo Rosasco, Silvia Villa
    On Learning The Optimal Regularization Parameter In Inverse Problems [pdf]
    Inverse Problems 40, (2024) DOI 10.1088/1361-6420/ad8a84
    Technical Report arXiv:2311.15845
  3. Francesca Bartolucci, Ernesto De Vito, Lorenzo Rosasco, Stefano Vigogna
    Understanding neural networks with reproducing kernel Banach spaces [pdf]
    ACHA 62 194-236 (2023)
    Technical Report arXiv:2109.09710
  4. S. Dahlke, F. De Mari, E. De Vito, M. Hansen, M. Hasannasab, M. Quellmalz, G. Steidl, G. Teschke
    Continuous Wavelet Frames on the Sphere: The Group-Theoretic Approach Revisited [pdf]
    ACHA 56 123-147 (2022)
    DOI: https://doi.org/10.1016/j.acha.2021.08.003
    Technical Report arXiv:2012.13460
  5. Zeljko Kereta, Stefano Vigogna, Valeriya Naumova, Lorenzo Rosasco, Ernesto De Vito
    Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel [pdf]
    Journal of Fourier Analysis and Applications 27 (2021)
    DOI: https://doi.org/10.1007/s00041-021-09835-0
    Technical Report arXiv:2006.09870
  6. Ernesto De Vito, Nicole Mücke, Lorenzo Rosasco
    Reproducing kernel Hilbert spaces on manifolds: Sobolev and Diffusion spaces [pdf]
    Analysis and Applications (2021) available online
    DOI: http://dx.doi.org/10.1142/S0219530520500220
  7. De Vito, E., Fornasier, M. and Naumova Valeriya
    A Machine Learning Approach to Optimal Tikhonov Regularization I: Affine Manifolds [pdf]
    Analysis and Applications, 20 (02) 353-400 (2022)
    DOI: http://dx.doi.org/10.1142/S0219530520500220
  8. Enrico Cecini, Ernesto De Vito, Lorenzo Rosasco
    Multi-Scale Vector Quantization with Reconstruction Trees [pdf]
    Information and Inference: A Journal of the IMA (2020) available online
    DOI http://dx.doi.org/10.1093/imaiai/iaa004
  9. Giovanni S. Alberti, Francesca Bartolucci, Filippo De Mari, Ernesto De Vito
    Unitarization and Inversion Formulae for the Radon Transform between Dual Pairs [pdf]
    SIAM Journal on Mathematical Analysis 51 (6) 4356-4381 (2019)
    DOI: http://dx.doi.org/10.1137/18M1225628
  10. S. Dahlke, F. De Mari, E. De Vito, L. Sawatzki, G. Steidl, G. Teschke, F. Voigtlaender
    On the atomic decomposition of coorbit spaces with non-integrable kernel [pdf]
    in Applied and Numerical Harmonic Analysis (2019) pp. 75-144
  11. D. Malafronte, E. De Vito, F. Odone
    Local Spatio-Temporal Representation Using the 3D Shearlet Transform
    Sampling Theory in Signal and Image Processing 17(1), 57-72 (2018)
  12. F. Bartolucci, F. De Mari, E. De Vito, F. Odone
    Shearlets as Multi-scale Radon Transforms
    Sampling Theory in Signal and Image Processing 17(1), 1-15 (2018)
  13. D. Malafronte, E. De Vito, F. Odone
    Space-Time Signal Analysis and the 3D Shearlet Transform [pdf]
    Journal of Mathematical Imaging and Vision 60(7), pp. 1008-1024 (2018)
    DOI -- http://dx.doi.org//10.1007/s10851-018-0791-3
  14. F. Bartolucci, F. De Mari, E. De Vito, F. Odone
    Radon transform intertwines shearlets and wavelets [pdf]
    Applied and Computational Harmonic Analysis (2018)
    DOI -- https://doi.org/10.1016/j.acha.2017.12.005
  15. A. Rudi, E. De Vito, A. Verri, F. Odone
    Regularized Kernel Algorithms for Support Estimation [pdf]
    Front. Appl. Math. Stat., 08 November (2017)
    DOI -- https://doi.org/10.3389/fams.2017.00023
  16. Duval-Poo, M., Noceti, N., Odone, F., and De Vito, E.
    Scale Invariant Interest Points with Shearlets [pdf]
    IEEE Transactions on Image Processing 26 (6) 2835-2867 (2017)
    DOI -- http://dx.doi.org//10.1109/TIP.2017.2687122
  17. Alberti, G.S., Dahlke, S. De Mari, F., De Vito, E. and Vigogna, S.
    Continuous and discrete frames generated by the evolution flow of the Schrödinger equation [pdf]
    Analysis and Applications 15 (6) 915-937 (2017)
    DOI: http://dx.doi.org/10.1142/S021953051750004X
  18. Dahlke, S., De Mari, F., De Vito, E., Labate, D., Steidl, G., Teschke, G., Vigogna, S.
    Coorbit spaces with voice in a Frechet space     [pdf]
    Journal of Fourier Analysis 23 (1) 141-206 (2017)
    DOI: http://dx.doi.org/10.1142/10.1007/s00041-016-9466-x
  19. De Mari, F., De Vito, E., Vigogna, S.
    Geometric classification of semidirect products in the maximal parabolic subgroup of Sp(2,R)     [pdf]
    Analysis and Application 15 (2) 241--259 (2017)
    DOI: http://dx.doi.org/10.1142/10.1142/S0219530515500256
  20. Dahlke, S., De Mari, F., De Vito, E., Hauser, S. Steidl, G., Teschke, G.
    Different faces of the shearlet group     [pdf]
    J. Geom. Anal. 26, 1693--1729 (2016)
    DOI: http://dx.doi.org/10.1007/s12220-015-9605-7
  21. Duval Poo M., Odone, F., De Vito, E.,
    Edges and corners with Shearlets [pdf]
    IEEE Trans. on Image Processing, 24 3768-3780 (2015)
    DOI: http://dx.doi.org/10.1109/TIP.2015.2451175 DOI
  22. De Vito, E., Rosasco L., Toigo A.
    Learning sets with separating kernels     [pdf]
    Applied and Computational Harmonic Analysis, 37 185--217 (2014)
  23. Alberti G., De Mari, F., De Vito, E., L. Mantovani
    Reproducing subgroups of Sp(2,R). Part II: admissible vectors [pdf]
    Monatshefte für Mathematik 173 261--307 (2014)
  24. Rudi A., De Vito, E., Odone, F.
    Geometrical and computational aspects of Spectral Support Estimation for novelty detection [pdf]
    Pattern Recognition Letters 36 107--116 (2014)
  25. Alberti G., L. Balletti, De Mari, F., De Vito, E.
    Reproducing subgroups of Sp(2,R). Part I: Algebraic Classification [pdf]
    Journal of Fourier Analysis and its Applications 19 651--682 (2013) on line
  26. De Vito, E., Villa, S.,  Umanità V.
    An extension of Mercer theorem to vector-valued measurable kernels[ pdf] 
    Applied Computational Harmonic Analysis, 34 339--351 (2013).
  27. De Mari, F., De Vito, E.
    A mock metaplectic representation     [pdf]
    Applied Computational Harmonic Analysis 34 163--200 (2013).
  28. De Vito, E., Villa, S.,  Umanità V.
    A consistent algorithm to solve Lasso, elastic-net and Tikhonov  regularization[pdf]
    Journal of Complexity 27 188–200 (2011).
  29. De Vito, E., Pereverzev S., Rosasco L.
    Adaptive Kernel Methods via the Balancing Principle     [pdf]
    Foundation of Computational Mathematics 8 355-479 (2010).
  30. Rosasco, L., Belkin, M., and De Vito, E.
    On Learning with Integral Operators     [pdf]
    Journal Machines Learning Reaserch 11 905-934 (2010).
  31. Carmeli C., De Vito E., Toigo A., Umanità
    Vector valued reproducing kernel Hilbert spaces and universality     [pdf]
    Analysis and Applicatiopns 8 19-61 (2010).
  32. Albini P., De Vito E., Toigo A.
    Quantum Homodyne Tomography as an Informationally Complete Positive Operator Valued Measure     [pdf]
    J. Phys. A: Math. Theor. 42 (2009) 29530.
  33. De Mol C., De Vito E., Rosasco L.
    Elastic Net Regularization in Learning Theory    .  [pdf]
    Journal of Complexity 25 201-230 (2009.
  34. A. Caponnetto, De Vito E., M. Pontil
    Entropy Conditions for $L_r$-Convergence of Empirical Processes    .  [pdf]
    Advances in Computational Mathematics 30 355--373 (2009).
  35. Lo Gerfo L., Rosasco L., Odone F., De Vito E., Verri A.
    Spectral Algorithms for Supervised Learning.  [pdf]
    Neural Computation, 7 1873-1897 (2008)
  36. Caponnetto A., De Vito E.
    Optimal Rates for Regularized Least-Squares Algorithm. [pdf]
    Foundations of Computational Mathematics, 7 331-368 (2007).
  37. C. Carmeli, E. De Vito, A. Toigo
    Vector Valued Reproducing Kernel Hilbert Spaces Integrable, Functions and Mercer Theorem. [pdf]
    Analysis and Applications, 4 377-408 (2006).
  38. De Vito E., Caponnetto A., Rosasco L.
    Discretization Error Analysis for Tikhonov Regularization in Learning Theory. [pdf]
    Analysis and Applications, 4 81-99 (2006).
  39. De Vito E., Rosasco L., Caponnetto A., De Giovannini U., Odone F.
    Learning from Examples as an Inverse Problem. [pdf]
    Journal of Machine Learning Research, 6 883-904 (2005).
  40. De Vito E., Caponnetto A., Rosasco L.
    Model Selection for Regularized Least-Squares Algorithm in Learning Theory. [pdf]
    Foundations of Computational Mathematics, 5 59-85 (2005).
  41. De Vito E., Rosasco L., Caponnetto A., Piana M., Verri A.
    Some Properties of Regularized Kernel Methods. [pdf]
    Journal of Machine Learning Research, 5 1363-1390 (2004).
  42. Rosasco L., De Vito E., Caponnetto A., Piana M., Verri A.
    Are Loss Functions All the Same? [pdf]
    Neural Computation, 16 1063-1076 (2004).
  43. C. Carmeli, G.Cassinelli, E. De Vito, A. Toigo, B. Vacchini
    A complete characterization of phase space measurements. [pdf]
    J.Phys. A, 37 5057-5066 (2004).
  44. G.Cassinelli, E. De Vito, A. Toigo
    Positive operator valued measures covariant with respect to an Abelian group. [pdf]
    J.Math. Phys., 45 418-433 (2004).
  45. G.Cassinelli, E. De Vito, A. Toigo
    Positive operator valued measures covariant with respect to an irreducible representation. [pdf]
    J. Math. Phys., 44 4768-4775 (2003).
  46. G.Cassinelli, E.De Vito
    Square-integrability modulo a subgroup. [ps]
    Trans. A.M.S., 355 1443-1465 (2003).
  47. G.Cassinelli, E.De Vito, P.Lahti, J.-P. Pellonpää
    Covariant localizations in the torus and the phase observables. [ps]
    J. Math. Phys., 43 693-704 (2002).
  48. P.Aniello, G.Cassinelli, E.De Vito, A.Levrero
    On discrete frames associated with semidirect products. [ps]
    J.Fourier Analys and Appl., 7 199-206 (2001).
  49. G. M. D'Ariano, E. De Vito, L. Maccone
    SU(1,1) tomography. [ps]
    Phys. Rev. A, 64 033805 (2001).
  50. P. Busch, G.Cassinelli, E.De Vito, P.Lahti, A.Levrero
    Teleportation and Measurement. [ps]
    Physics Letter A, 284 141-145 (2001).
  51. G.Cassinelli, E.De Vito, P.Lahti, A.Levrero
    Phase Space Observables and Isotypic Spaces. [ps]
    J.Math.Phys., 41 5883-5896 (2000).
  52. G.Cassinelli, E.De Vito, A.Levrero
    Square-integrable imprimitivity systems. [ps]
    J.Math.Phys., 41 4833-4859 (2000).
  53. G.Cassinelli, G.M. D'Ariano, E.De Vito, A.Levrero
    Group theoretical Quantum Tomography. [ps]
    J.Math.Phys 41 7940-7951 (2000).
  54. G.Cassinelli, E.De Vito, P.Lahti, A.Levrero
    A theorem of Ludwig revisited. [ps]
    Found.Phys., 1755-1761 30 (2000).
  55. P.Aniello, G.Cassinelli, E.De Vito, A.Levrero
    Frames associetad with imprimitivity systems. [ps]
    J. Math. Phys., 40 5184-5202 (1999).
  56. P.Aniello, G.Cassinelli, E.De Vito, A.Levrero
    Wavelet transforms and discrete frames associated to semidirect products. [ps]
    J. Math. Phys., 39 3965-3973 (1998).
  57. P.Aniello, G.Cassinelli, E.De Vito, A.Levrero
    Square integrability of induced representations of semidirect products with normal abelian subgroup. [ps]
    Rev. Math. Phys., 10 301-313 (1998).
  58. G.Cassinelli, E.De Vito, A.Levrero
    Galilei invariant wave equations. [ps]
    Rep.Math.Phys., 43 467-498 (1999).
  59. G.Cassinelli, E.De Vito, P.Lahti, A.Levrero
    Symmetry of the Quantum State Space and Group Representations. [ps]
    Rev. Math. Phys., 10 893-924 (1998).
  60. G.Cassinelli, E.De Vito, P.Lahti, A.Levrero
    Symmetry Groups in Quantum Mechanics and the Theorem of Wigner on the Symmetry Transformations. [ps]
    Rev. Math. Phys., 9 921-941 (1997).
  61. G.Cassinelli, E.De Vito, A.Levrero
    Integrability of the Quantum Adiabatic Evolution and Geometric Phases. [ps]
    J. Math. Phys., 38 6101-6118 (1997).
  62. G.Cassinelli, E.De Vito, A.Levrero
    On the decomposition of a quantum state. [ps]
    J. Math. Analysis and Appl., 210 472-483 (1997).
  63. De Vito, E.,  Truini, P.
    Deformation of polynomial spaces over semisimple Lie groups    .
    Comm. Theoret. Phys. (Allahabad) 3  1–34 (1994)
  64. Cassinelli, G. ; De Vito, E. ; Lahti, P.
    Properties of the range of a state operator
    Rep. Math. Phys. 34  211–224 (1994)
  65. E.De Vito, A.Levrero
    Pancharatnam Phase for Polarized     Light
    J.Mod. Opt.,  41 2233 (1994).
  66. G.Cassinelli, E.De Vito, P.Lahti, A.Levrero
    Geometric Phase and Sequential Measurements in Quantum Mechanics
    Phys. Rev. A 49, 3229-3233 (1994).

Conference Papers (back)

  1. Stefano Vigogna, Giacomo Meanti, Ernesto De Vito, Lorenzo Rosasco
    Multiclass learning with margin: exponential rates with no bias-variance trade-off [pdf]
    ICML2022
  2. Giacomo Meanti, Luigi Carratino, Ernesto De Vito, Lorenzo Rosasco
    Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression [pdf]
    AISTATS 2022
  3. Antoine Chatalic, Luigi Carratino, Ernesto De Vito, Lorenzo Rosasco
    Mean Nyström Embeddings for Adaptive Compressive Learning [pdf]
    AISTATS 2022
  4. Giovanni S. Alberti, Ernesto De Vito, Matti Lassas, Luca Ratti, Matteo Santacesaria
    Learning the optimal Tikhonov regularizer for inverse problems [pdf]
    NIPS2021
  5. Andrea Della Vecchia, Jaouad Mourtada, Ernesto De Vito, Lorenzo Rosasco
    Regularized ERM on random subspaces [pdf]
    AISTATS 2021
  6. Zeljko Kereta, Stefano Vigogna, Valeriya Naumova, Lorenzo Rosasco, Ernesto De Vito
    Monte Carlo wavelets: A randomized approach to frame discretization [pdf]
    13th International Conference on Sampling Theory and Applications, SampTA 2019
    DOI: http://dx.doi.org/10.1109/SampTA45681.2019.9030825
  7. Duval-Poo M. , Noceti N., Odone F., De Vito E.
    Detection and description of scale invariant interest points with shearlets   [pdf]
    Conference proceedings: SampTA 2017 Page(s):294 - 298 -- DOI: 10.1109/SAMPTA.2017.8024340
  8. Bartolucci F., De Mari F., De Vito E., Odone F.,
    Shearlets as multi-scale Radon transform   [pdf]
    Conference proceedings: SampTA 2017 Page(s): 625 - 629 -- DOI: 10.1109/SAMPTA.2017.8024400
  9. Malafronte D. , Odone F., De Vito E.
    Local spatio-temporal representation using the 3D shearlet transform   [pdf]
    Conference proceedings: SampTA 2017 Page(s): 585-589 -- DOI: 10.1109/SAMPTA.2017.8024409
  10. Duval-Poo M. , Levet F. De Vito E., Odone F.
    Retinal Image Analysis with Shearlets   [pdf]
    Conference proceedings: STAG: Smart Tools and Apps in computer Graphics (2016)
  11. Duval-Poo M. , Odone F., De Vito E.
    Enhancing signal discontinuities with Shearlets: an application to corner detection  [pdf]
    Conference proceedings: ICIAP 2015
  12. De Vito, E., Rosasco L., Toigo A.
    Spectral Regularization for Support Estimation  [pdf]
    Conference proceedings: Twenty-Fourth Annual Conference on Neural Information Processing Systems, 2010.
  13. De Mari, F, De Vito E.
    An introduction to mocklets
    Oberwolfach Mini-Workshop: Shearlets, Organised by Gitta Kutyniok, Demetrio Labate, October 3rd – October 9th, 2010 [pdf]
  14. De Mol C., De Vito E., Rosasco L.
    Sparsity in Learning Theory
    Oberwolfach Mini-Workshop: Wavelet and Multiscale Methods, Organised by A. Cohen, W. Dahmen, R. DeVore, August 1st – August 7th, 2010 [pdf]
  15. Rosasco, L., Belkin, M., and De Vito, E.
    A Note on Perturbation Results for Learning Empirical Operators     [pdf]
    COLT 2009-- 22nd Annual Conference on Learning Theory (2009).
  16. De Mol C., De Vito E., Rosasco L.
    Analysis of Elastic-Net Regularization
    Oberwolfach Mini-Workshop: Learning Theory and Approximation, Organised by  K. Jetter,  S. Smale, D. Zhou,  June 29th – July 5th, 2008  [pdf]
  17. Rosasco L., Caponnetto A., De Vito E., De Giovannini U., Odone F.
    Learning, Regularization and Ill-Posed Inverse Problems. [pdf]
    Conference proceedings: Eighteenth Annual Conference on Neural Information Processing Systems, 2004.
  18. G. Cassinelli, E. De Vito, P. Truini
    Classical pairing and quantum group duality.
    Quantum symmetries (Clausthal, 1991), 373–379, World Sci. Publ., River Edge, NJ, 1993.

Chapters in Books (back)
  1. Bartolucci,F., De Mari, Filippo, De Vito, E.
    Cone-Adapted Shearlets and Radon Transforms
    in ``Advances in Microlocal and Time-Frequency Analysis'', Boggiatto, Cappiello, Cordero, Coriasco, Garello, Oliaro, Seiler (eds.), Applied and Numerical Harmonic Analysis (2020), DOI 10.1007/978-3-030-36138-9
  2. Alberti, G.S., Dahlke, S. De Mari, F., De Vito, E. and Fuhr, H.
    Recent Progress in Shearlet Theory: Systematic Construction of Shearlet Dilation Groups, Characterization of Wavefront Sets, and New Embeddings [pdf]
    in ``Frames and Other Bases in Abstract and Function Spaces'', I. Pesenson et al. (eds.), Applied and Numerical Harmonic Analysis (2017), DOI 10.1007/978-3-319-55550-8_7
  3. De Mari, F., De Vito, E.
    The Use of Representations in Applied Harmonic Analysis
    in ``Harmonic and Applied Analysis. From Groups to Signals'', Dahlke, S., De Mari, F., Grohs, P., Labate, D. (Eds.),
    Birkhasuer (2015) DOI 10.1007/978-3-319-18863-8 [ link to Springer online catalogueonline catalogue]
  4. Rudi, A, Canas, G., De Vito, E., Rosasco, R.
    Learning Sets and Subspaces [pdf]
    in "Regularization, Optimization, Kernel and Support Vector Machines", Ed. Suykens, J., Signoretto, M., Argyriou, A., Chapman & Hall/CRC, 2014
  5. G. Cassinelli, E. De Vito, A. Levrero, P. J. Lahti
    The Theory of Symmetry Actions in Quantum Mechanics with an application to the Galilei group.
    Series: Lecture Notes in Physics, Vol.  654 2004, XII, 112 p.
    [link to Springer online catalogue]
Old Technical Reports (back)
  1. Rosasco L., De Vito E. and Verri A.
    Spectral Methods for Regularization in Learning Theory. [pdf]
    Technical report DISI-TR-05-18. 
  2. Caponnetto A., Rosasco L., De Vito E., Verri A.
    Empirical Effective Dimension and Optimal Rates for Regularized Least-Squares Algorithm. [pdf]
    CBCL Paper #252/AI Memo #2005-019, Massachusetts Institute of Technology, Cambridge, MA, May 2005.


Home.