Reliable and cost-effective large scale machine learning

Información del proyecto

REAL

Identificador del acuerdo de subvención: 947908

DOI

10.3030/947908

Fecha de la firma de la CE 29 Septiembre 2020

Fecha de inicio 1 Abril 2021

Fecha de finalización 31 Marzo 2026

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 498 830,00

Aportación de la UE

€ 1 498 830,00

Coordinado por

UNIVERSITA COMMERCIALE LUIGI BOCCONI
Italy

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Open Research Data Pilot (1)

Data Management Plan (DMP)

Participation in the Open Research Data Pilot

Publicaciones

Conference proceedings (13)

Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares

Autores: Blake Woodworth, Francis Bach, Alessandro Rudi
Publicado en: Conference on Learning Theory, 2022
Editor: COLT

On the Consistency of Max-Margin Losses

Autores: Alex Nowak-Vila, Alessandro Rudi, Francis Bach
Publicado en: AISTATS, 2021
Editor: AISTATS

On the Benefits of Large Learning Rates for Kernel Methods

Autores: Gaspard Beugnot, Julien Mairal, Alessandro Rudi
Publicado en: Conference on Learning Theory, 2022
Editor: COLT

PSD Representations for Effective Probability Models

Autores: Rudi, Alessandro; Ciliberto, Carlo
Publicado en: Edición 1, 2021
Editor: NeurIPS

Measuring dissimilarity with diffeomorphism invariance

Autores: Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj, Alessandro Rudi
Publicado en: International Conference on Machine Learning, 2022
Editor: ICML

Sampling from Arbitrary Functions via PSD Models

Autores: Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi
Publicado en: International Conference of Machine Learning, 2022
Editor: ICML

Beyond Tikhonov: Faster Learning with Self-Concordant Losses via Iterative Regularization

Autores: Beugnot, Gaspard; Mairal, Julien; Rudi, Alessandro
Publicado en: NeurIPS 2021 – 35th Annual Conference on Neural Information Processing Systems, Edición 1, 2021
Editor: NeurIPS

Mixability made efficient: Fast online multiclass logistic regression.

Autores: Rémi Jézéquel, Pierre Gaillard, Alessandro Rudi
Publicado en: Advances in Neural Information Processing Systems 34 (2021)., 2021
Editor: Neural Information Processing Systems

Active Labeling: Streaming Stochastic Gradients

Autores: Vivien Cabannes, Francis Bach, Vianney Perchet, Alessandro Rudi
Publicado en: NeurIPS 2021, 2021
Editor: NeurIPS

Fast Rates for Structured Prediction

Autores: Vivien Cabannes, Francis Bach, Alessandro Rudi
Publicado en: Proceedings of Thirty Fourth Conference on Learning Theory, 2021
Editor: Proceedings of Machine Learning Research

Disambiguation of weak supervision with exponential convergence rates

Autores: Vivien Cabannes, Francis Bach, Alessandro Rudi
Publicado en: Proceedings of the 38th International Conference on Machine Learning,, 2021
Editor: ICML

Nyström Kernel Mean Embeddings

Autores: Antoine Chatalic, Nicolas Schreuder, Alessandro Rudi, Lorenzo Rosasco
Publicado en: International Conference of Machine Learning, 2022
Editor: ICML

Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning

Autores: Vivien Cabannes, Loucas Pillaud-Vivien, Francis Bach, Alessandro Rudi
Publicado en: NeurIPS, 2021
Editor: NeurIPS

Other (8)

A Dimension-free Computational Upper-bound for Smooth Optimal Transport Estimation

Autores: Adrien Vacher, Boris Muzellec, Alessandro Rudi, Francis Bach, Francois-Xavier Vialard
Publicado en: 2021
Editor: Arxiv

A Note on Optimizing Distributions using Kernel Mean Embeddings

Autores: Muzellec, Boris; Bach, Francis; Rudi, Alessandro
Publicado en: https://hal.archives-ouvertes.fr/hal-03454259, 2021
Editor: HAL
DOI: 10.48550/arxiv.2106.09994

Exponential convergence of sum-of-squares hierarchies for trigonometric polynomials

Autores: Francis Bach, Alessandro Rudi
Publicado en: 2022
Editor: Arxiv

Near-optimal estimation of smooth transport maps with kernel sums-of-squares

Autores: Boris Muzellec, Adrien Vacher, Francis Bach, François-Xavier Vialard, Alessandro Rudi
Publicado en: 2022
Editor: Arxiv

Finding Global Minima via Kernel Approximations

Autores: Alessandro Rudi, Ulysse Marteau-Ferey, Francis Bach
Publicado en: 2021
Editor: Arxiv

Learning PSD-valued functions using kernel sums-of-squares

Autores: Boris Muzellec, Francis Bach, Alessandro Rudi
Publicado en: 2022
Editor: Arxiv

Infinite-Dimensional Sums-of-Squares for Optimal Control

Autores: Eloïse Berthier, Justin Carpentier, Alessandro Rudi, Francis Bach
Publicado en: 2021
Editor: Arxiv

Second order conditions to decompose smooth functions as sums of squares

Autores: Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi
Publicado en: 2022
Editor: Arxix

Peer reviewed articles (5)

Optimal Estimation of Smooth Transport Maps with Kernel SoS

Autores: Adrien Vacher; Boris Muzellec; Francis Bach; François-Xavier Vialard; Alessandro Rudi
Publicado en: SIAM Journal on Mathematics of Data Science, Edición 43, 2024, ISSN 2577-0187
Editor: SIAM
DOI: 10.1137/22m1528847

Tropical Reproducing Kernels and Optimization

Autores: Pierre-Cyril Aubin-Frankowski; Stéphane Gaubert
Publicado en: Integral Equations and Operator Theory, Edición 15, 2024, ISSN 1420-8989
Editor: Springer
DOI: 10.1007/s00020-024-02769-4

Finding global minima via kernel approximations

Autores: Alessandro Rudi; Ulysse Marteau-Ferey; Francis Bach
Publicado en: Mathematical Programming, Edición 34, 2024, ISSN 1436-4646
Editor: Springer
DOI: 10.1007/s10107-024-02081-4

Quantitative Gaussian approximation of randomly initialized deep neural networks

Autores: Basteri, A.; Trevisan, D.
Publicado en: Machine Learning, Edición 25, 2024, ISSN 1573-0565
Editor: Springer
DOI: 10.1007/s10994-024-06578-z

Vector-Valued Least-Squares Regression under Output Regularity Assumptions

Autores: Luc Brogat-Motte, Alessandro Rudi, Céline Brouard, Juho Rousu, Florence d'Alché-Buc
Publicado en: Journal of Machine Learning Research, Edición Volume 23, 2022, ISSN 1533-7928
Editor: JMLR