Efficient algorithms for sustainable machine learning

Fast object segmentation learning with kernel-based methods for robotics

Autori: Federico Ceola, Elisa Maiettini, Giulia Pasquale, Lorenzo Rosasco, Lorenzo Natale
Pubblicato in: 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021, Pagina/e 13581-13588
Editore: IEEE

An optimal structured zeroth-order algorithm for non-smooth optimization

Autori: Marco Rando, Cesare Molinari, Lorenzo Rosasco, Silvia Villa
Pubblicato in: Advances in Neural Information Processing Systems, Numero 36, 2024
Editore: Advances in Neural Information Processing Systems

Efficient Unsupervised Learning for Plankton Images

Autori: P. D. Alfano; M. Rando; M. Letizia; F. Odone; L. Rosasco; V. P. Pastore
Pubblicato in: 2022 26th International Conference on Pattern Recognition (ICPR), 2022
Editore: IEEE
DOI: 10.1109/icpr56361.2022.9956360

Snacks: a fast large-scale kernel SVM solver

Autori: Tanji, Sofiane; Vecchia, Andrea Della; Glineur, François; Villa, Silvia; 2023 European Control Conference (ECC)
Pubblicato in: 2023 European Control Conference (ECC), Numero 4, 2023, Pagina/e 1-6
Editore: IEEE
DOI: 10.23919/ecc57647.2023.10178323

Mean nyström embeddings for adaptive compressive learning

Autori: Antoine Chatalic, Luigi Carratino, Ernesto De Vito, Lorenzo Rosasco
Pubblicato in: International Conference on Artificial Intelligence and Statistics, 2022, Pagina/e 9869-9889
Editore: PMLR

Decentralised learning with random features and distributed gradient descent

Autori: Dominic Richards, Patrick Rebeschini, Lorenzo Rosasco
Pubblicato in: Proceedings of Machine Learning Research, 2020
Editore: JMLR, Inc. and Microtome Publishing

Iterative regularization for convex regularizers

Autori: Cesare Molinari, Mathurin Massias, Lorenzo Rosasco, Silvia Villa
Pubblicato in: Proceedings of Machine Learning Research, Numero 130, 2021, Pagina/e 1684-1692
Editore: JMLR, Inc. and Microtome Publishing

Ada-BKB: Scalable Gaussian Process Optimization on Continuous Domains by Adaptive Discretization

Autori: Rando, Marco; Carratino, Luigi; Villa, Silvia; Rosasco, Lorenzo
Pubblicato in: International Conference on Artificial Intelligence and Statistics, Numero 9, 2022, Pagina/e 320-7348
Editore: PLMR
DOI: 10.48550/arxiv.2106.08598

Gain with no pain: Efficiency of kernel-PCA by Nyström sampling

Autori: Nicholas Sterge, Bharath Sriperumbudur, Lorenzo Rosasco, Alessandro Rudi
Pubblicato in: International Conference on Artificial Intelligence and Statistics, 2020, Pagina/e 3642-3652
Editore: AISTATS

Nyström Kernel Mean Embeddings

Autori: Antoine Chatalic, Nicolas Schreuder, Lorenzo Rosasco, Alessandro Rudi
Pubblicato in: International Conference on Machine Learning, 2022
Editore: PMLR

Estimating Koopman operators with sketching to provably learn large scale dynamical systems

Autori: Meanti, Giacomo; Chatalic, Antoine; Kostic, Vladimir R.; Novelli, Pietro; Pontil, Massimiliano; Rosasco, Lorenzo
Pubblicato in: Proceedings of the 37th International Conference on Neural Information Processing Systems, Numero 12, 2023, Pagina/e 77242–77276
Editore: Curran Associates
DOI: 10.48550/arxiv.2306.04520

Asymptotics of Ridge(less) Regression under General Source Condition

Autori: Dominic Richards, Jaouad Mourtada, Lorenzo Rosasco
Pubblicato in: Proceedings of Machine Learning Research, Numero 130, 2021, Pagina/e 3889-3897
Editore: JMLR, Inc. and Microtome Publishing

Efficient kernel methods for model-independent new physics searches

Autori: Marco Letizia, Gianvito Losapio, Marco Rando, Gaia Grosso, Lorenzo Rosasco
Pubblicato in: NeurIPS 2022 workshop: Machine Learning and the Physical Sciences, 2021
Editore: NeurIPS
DOI: 10.5281/zenodo.5536345

Multiclass learning with margin: exponential rates with no bias-variance trade-off

Autori: Stefano Vigogna, Giacomo Meanti, Ernesto De Vito, Lorenzo Rosasco
Pubblicato in: International Conference on Machine Learning, 2022
Editore: Association for Computing Machinery

Hyperbolic manifold regression

Autori: Gian Maria Marconi, Carlo Ciliberto, Lorenzo Rosasco
Pubblicato in: Proceedings of Machine Learning Research, 2020
Editore: JMLR, Inc. and Microtome Publishing

Regularized ERM on random subspaces

Autori: Andrea Della Vecchia, Jaouad Mourtada, Ernesto De Vito, Lorenzo Rosasco
Pubblicato in: Proceedings of Machine Learning Research, Numero 130, 2021, Pagina/e 4006-4014
Editore: JMLR, Inc. and Microtome Publishing

Fair learning with Wasserstein barycenters for non-decomposable performance measures

Autori: Solenne Gaucher, Nicolas Schreuder, Evgenii Chzhen
Pubblicato in: International Conference on Artificial Intelligence and Statistics, Numero 2436-2459, 2023
Editore: PMLR

A fast and flexible machine learning approach to data quality monitoring

Autori: Grosso, Gaia; Lai, Nicolò; Letizia, Marco; Pazzini, Jacopo; Rando, Marco; Wulzer, Andrea; Zanetti, Marco
Pubblicato in: NeurIPS 2022 workshop: Machine Learning and the Physical Sciences, Numero 1, 2023
Editore: NeurIPS
DOI: 10.48550/arxiv.2301.08917

Kernel methods through the roof: Handling billions of points efficiently

Autori: Giacomo Meanti, Luigi Carratino, Lorenzo Rosasco, Alessandro Rudi
Pubblicato in: Advances in Neural Information Processing Systems, 2020
Editore: Neural information processing systems foundation

Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression

Autori: Giacomo Meanti, Luigi Carratino, Ernesto De Vito, Lorenzo Rosasco
Pubblicato in: International Conference on Artificial Intelligence and Statistics, 2022, Pagina/e 6554-6572
Editore: PMLR

Regularization Properties of Dual Subgradient Flow

Autori: Apidopoulos, Vassilis; Molinari, Cesare; Rosasco, Lorenzo; Villa, Silvia
Pubblicato in: 2023 European Control Conference ({ECC}), Numero 4, 2023, Pagina/e 1-8
Editore: IEEE
DOI: 10.23919/ecc57647.2023.10178128

Near-linear time gaussian process optimization with adaptive batching and resparsification

Autori: Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco
Pubblicato in: Proceedings of Machine Learning Research, Numero 119, 2020, Pagina/e 1295-1305
Editore: JMLR, Inc. and Microtome Publishing

Park: Sound and efficient kernel ridge regression by feature space partitions

Autori: Luigi Carratino, Stefano Vigogna, Daniele Calandriello, Lorenzo Rosasco
Pubblicato in: Advances in Neural Information Processing Systems, Numero 34, 2021, Pagina/e 6430-6441
Editore: NeuIPS

Heteroscedastic Gaussian Processes and Random Features: Scalable Motion Primitives with Guarantees

Autori: Caldarelli, E; Chatalic, A; Colome, A; Rosasco, L; Torras, C
Pubblicato in: 7th Conference on Robot Learning (CoRL 2023), 2023
Editore: MLR Press

Anderson acceleration of coordinate descent

Autori: Quentin Bertrand, Mathurin Massias
Pubblicato in: Proceedings of Machine Learning Research, Numero 130, 2021, Pagina/e 1288-1296
Editore: JMLR, Inc. and Microtome Publishing

Fast approximation of orthogonal matrices and application to PCA

Autori: Christian Rusu, Lorenzo Rosasco
Pubblicato in: Signal processing, Volume 194, 2022, ISSN 0165-1684
Editore: Elsevier BV
DOI: 10.1016/j.sigpro.2021.108451

On the emergence of whole-body strategies from humanoid robot push-recovery learning

Autori: Diego Ferigo, Raffaello Camoriano, Paolo Maria Viceconte, Daniele Calandriello, Silvio Traversaro, Lorenzo Rosasco, Daniele Pucci
Pubblicato in: IEEE Robotics and Automation Letters, 2021, ISSN 2377-3766
Editore: Institute of Electrical and Electronics Engineers Inc.

Multi-scale vector quantization with reconstruction trees

Autori: Enrico Cecini, Ernesto De Vito, Lorenzo Rosasco
Pubblicato in: Information and Inference: A Journal of the IMA, 2021, Pagina/e 955-986, ISSN 2049-8772
Editore: Oxford University Press

A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings

Autori: Carlo Ciliberto, Lorenzo Rosasco, Alessandro Rudi
Pubblicato in: J. Mach. Learn. Res., 2020, ISSN 1532-4435
Editore: MIT Press

Convergence rates for the Heavy-Ball continuous dynamics for non-convex optimization, under Polyak-\L ojasiewicz condition

Autori: Apidopoulos, Vassilis; Ginatta, Nicolò; Villa, Silvia
Pubblicato in: Journal of Global Optimization, Numero 8, 2022, ISSN 0925-5001
Editore: Kluwer Academic Publishers

An elementary analysis of ridge regression with random design

Autori: Jaouad Mourtada, Lorenzo Rosasco
Pubblicato in: Comptes Rendus. Mathématique, 2022, ISSN 1778-3569
Editore: Academie des sciences

Accelerated Iterative Regularization via Dual Diagonal Descent

Autori: Luca Calatroni, Guillaume Garrigos, Lorenzo Rosasco, Silvia Villa
Pubblicato in: SIAM Journal on Optimization, 2021, ISSN 1052-6234
Editore: Society for Industrial and Applied Mathematics
DOI: 10.1137/19m1308888

Construction and Monte Carlo Estimation of Wavelet Frames Generated by a Reproducing Kernel

Autori: Ernesto De Vito, Zeljko Kereta, Valeriya Naumova, Lorenzo Rosasco, Stefano Vigogna
Pubblicato in: Journal of Fourier Analysis and Applications, Numero 27/2, 2021, ISSN 1069-5869
Editore: Birkhaeuser
DOI: 10.1007/s00041-021-09835-0

Iterative regularization for low complexity regularizers

Autori: Molinari, Cesare; Massias, Mathurin; Rosasco, Lorenzo; Villa, Silvia
Pubblicato in: Numerische Mathematik, Numero Volume 156, 2024, Pagina/e 641–689, ISSN 0029-599X
Editore: Springer Verlag
DOI: 10.1007/s00211-023-01390-8

Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry

Autori: Guillaume Garrigos, Lorenzo Rosasco, Silvia Villa
Pubblicato in: Mathematical Programming, 2022, Pagina/e 1-60, ISSN 0025-5610
Editore: Springer Verlag

Goodness of fit by Neyman-Pearson testing

Autori: Grosso, Gaia; Letizia, Marco; Pierini, Maurizio; Wulzer, Andrea
Pubblicato in: SciPost Physics, Numero Volume 16, Number 5, 2024, ISSN 2542-4653
Editore: SciPost Foundation
DOI: 10.48550/arxiv.2305.14137

Implicit regularization with strongly convex bias: stability and acceleration

Autori: Silvia Villa, Simon Matet, Bằng Công Vũ, Lorenzo Rosasco
Pubblicato in: Analysis and Applications, 2022, ISSN 0219-5305
Editore: World Scientific

Learning to Avoid Obstacles With Minimal Intervention Control

Autori: Anqing Duan, Raffaello Camoriano, Diego Ferigo, Yanlong Huang, Daniele Calandriello, Lorenzo Rosasco, Daniele Pucci
Pubblicato in: Frontiers in Robotics and AI, Numero 7, 2020, ISSN 2296-9144
Editore: Frontiers Media S.A.
DOI: 10.3389/frobt.2020.00060

Understanding neural networks with reproducing kernel Banach spaces

Autori: Ernesto De Vito, Lorenzo Rosasco
Pubblicato in: Applied and Computational Harmonic Analysis, Numero 62, 2023, Pagina/e 194-236, ISSN 1096-603X
Editore: Academic Press Inc.
DOI: 10.1016/j.acha.2022.08.006

Reproducing kernel Hilbert spaces on manifolds: Sobolev and diffusion spaces

Autori: Ernesto De Vito, Nicole Mücke, Lorenzo Rosasco
Pubblicato in: Analysis and Applications, Numero 19-03, 2021, Pagina/e 363-396, ISSN 1793-6861
Editore: World Scientific Publishing Co. Pte Ltd
DOI: 10.1142/s0219530520400114

Structured prediction for CRiSP inverse kinematics learning with misspecified robot models

Autori: Gian Maria Marconi, Raffaello Camoriano, Lorenzo Rosasco, Carlo Ciliberto
Pubblicato in: IEEE Robotics and Automation Letters, 2021, ISSN 2377-3766
Editore: Institute of Electrical and Electronics Engineers Inc.

Faster kriging: Facing high-dimensional simulators

Autori: Xuefei Lu, Alessandro Rudi, Emanuele Borgonovo, Lorenzo Rosasco
Pubblicato in: Operations Research, 2020, ISSN 0030-364X
Editore: Institute for Operations Research and the Management Sciences

On-line object detection: a robotics challenge

Autori: Elisa Maiettini, Giulia Pasquale, Lorenzo Rosasco, Lorenzo Natale
Pubblicato in: Autonomous Robots, 2020, ISSN 1573-7527
Editore: Springer Netherlands

Top-tuning: A study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods

Autori: Alfano P. D.; Pastore V. P.; Rosasco L.; Odone F.
Pubblicato in: Image and Vision Computing, Numero Volume 142, 2024, ISSN 0262-8856
Editore: Elsevier BV
DOI: 10.1016/j.imavis.2023.104894

Adherent: Learning human-like trajectory generators for whole-body control of humanoid robots

Autori: Paolo Maria Viceconte, Raffaello Camoriano, Giulio Romualdi, Diego Ferigo, Stefano Dafarra, Silvio Traversaro, Giuseppe Oriolo, Lorenzo Rosasco, Daniele Pucci
Pubblicato in: IEEE Robotics and Automation Letters, Numero 7-2, 2022, Pagina/e 2779-2786, ISSN 2377-3766
Editore: IEEE

Constructing fast approximate eigenspaces with application to the fast graph Fourier transforms

Autori: Cristian Rusu, Lorenzo Rosasco
Pubblicato in: IEEE Transactions on Signal Processing, 2021, Pagina/e 1-1, ISSN 1053-587X
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tsp.2021.3107629

Learning new physics efficiently with nonparametric methods

Autori: Marco Letizia; Gianvito Losapio; Marco Rando; Gaia Grosso; Andrea Wulzer; Maurizio Pierini; Marco Zanetti; Lorenzo Rosasco
Pubblicato in: European Physical Journal, Numero 6, 2022, ISSN 1434-6044
Editore: Springer Verlag
DOI: 10.1140/epjc/s10052-022-10830-y

Zeroth-order optimization with orthogonal random directions

Autori: David Kozak; Cesare Molinari; Lorenzo Rosasco; Luis Tenorio; Silvia Villa
Pubblicato in: Mathematical Programming, Numero 6, 2022, ISSN 0025-5610
Editore: Springer Verlag
DOI: 10.1007/s10107-022-01866-9

Convergence of an asynchronous block-coordinate forward-backward algorithm for convex composite optimization

Autori: Cheik Traoré; Saverio Salzo; Silvia Villa
Pubblicato in: Computational Optimization and Applications, Numero 86, 2023, Pagina/e 303–344, ISSN 0926-6003
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10589-023-00489-w

Physics informed machine learning for wind speed prediction

Autori: Daniele Lagomarsino-Oneto, Giacomo Meanti, Nicolò Pagliana, Alessandro Verri, Andrea Mazzino, Lorenzo Rosasco, Agnese Seminara
Pubblicato in: Energy, 2023, ISSN 0360-5442
Editore: Pergamon Press Ltd.

Learn Fast, Segment Well: Fast Object Segmentation Learning on the iCub Robot

Autori: Federico Ceola; Elisa Maiettini; Giulia Pasquale; Giacomo Meanti; Lorenzo Rosasco; Lorenzo Natale
Pubblicato in: IEEE Transactions on Robotics, Numero 2, 2022, Pagina/e 3154-3172, ISSN 1552-3098
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tro.2022.3164331

Fast iterative regularization by reusing data

Autori: Cristian Vega; Cesare Molinari; Lorenzo Rosasco; Silvia Villa
Pubblicato in: Journal of Inverse and Ill-posed Problems, Numero 3, 2023, ISSN 0928-0219
Editore: Walter de Gruyter GmbH & Co. KG
DOI: 10.1515/jiip-2023-0009

Fast kernel methods for data quality monitoring as a goodness-of-fit test

Autori: Gaia Grosso; Nicolò Lai; Marco Letizia; Jacopo Pazzini; Marco Rando; Lorenzo Rosasco; Andrea Wulzer; Marco Zanetti
Pubblicato in: Machine Learning: Science and Technology, 4 (3) 035029, Numero 6, 2023, ISSN 2632-2153
Editore: Institute of Physics Publishing
DOI: 10.1088/2632-2153/acebb7

Regularization: From inverse problems to large-scale machine learning

Autori: Ernesto De Vito, Lorenzo Rosasco, Alessandro Rudi
Pubblicato in: 2021, Pagina/e 245-296
Editore: Springer International Publishing AG

Pubblicazioni

Condividi questa pagina Condividi questa pagina sui social network

Scarica Scarica il contenuto della pagina