Reliable and cost-effective large scale machine learning

Project Information

REAL

Grant agreement ID: 947908

DOI 10.3030/947908

EC signature date 29 September 2020

Start date 1 April 2021

End date 31 March 2026

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost € 1 498 830,00

EU contribution € 1 498 830,00

Coordinated by

INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET AUTOMATIQUE
France

Deliverables

Open Research Data Pilot (1)

Data Management Plan (DMP)

Participation in the Open Research Data Pilot

Publications

Conference proceedings (13)

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

Author(s): Blake Woodworth, Francis Bach, Alessandro Rudi
Published in: Conference on Learning Theory, 2022
Publisher: COLT

On the Consistency of Max-Margin Losses

Author(s): Alex Nowak-Vila, Alessandro Rudi, Francis Bach
Published in: AISTATS, 2021
Publisher: AISTATS

On the Benefits of Large Learning Rates for Kernel Methods

Author(s): Gaspard Beugnot, Julien Mairal, Alessandro Rudi
Published in: Conference on Learning Theory, 2022
Publisher: COLT

PSD Representations for Effective Probability Models

Author(s): Rudi, Alessandro; Ciliberto, Carlo
Published in: Issue 1, 2021
Publisher: NeurIPS

Measuring dissimilarity with diffeomorphism invariance

Author(s): Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj, Alessandro Rudi
Published in: International Conference on Machine Learning, 2022
Publisher: ICML

Sampling from Arbitrary Functions via PSD Models

Author(s): Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi
Published in: International Conference of Machine Learning, 2022
Publisher: ICML

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

Author(s): Beugnot, Gaspard; Mairal, Julien; Rudi, Alessandro
Published in: NeurIPS 2021 – 35th Annual Conference on Neural Information Processing Systems, Issue 1, 2021
Publisher: NeurIPS

Mixability made efficient: Fast online multiclass logistic regression.

Author(s): Rémi Jézéquel, Pierre Gaillard, Alessandro Rudi
Published in: Advances in Neural Information Processing Systems 34 (2021)., 2021
Publisher: Neural Information Processing Systems

Active Labeling: Streaming Stochastic Gradients

Author(s): Vivien Cabannes, Francis Bach, Vianney Perchet, Alessandro Rudi
Published in: NeurIPS 2021, 2021
Publisher: NeurIPS

Fast Rates for Structured Prediction

Author(s): Vivien Cabannes, Francis Bach, Alessandro Rudi
Published in: Proceedings of Thirty Fourth Conference on Learning Theory, 2021
Publisher: Proceedings of Machine Learning Research

Disambiguation of weak supervision with exponential convergence rates

Author(s): Vivien Cabannes, Francis Bach, Alessandro Rudi
Published in: Proceedings of the 38th International Conference on Machine Learning,, 2021
Publisher: ICML

Nyström Kernel Mean Embeddings

Author(s): Antoine Chatalic, Nicolas Schreuder, Alessandro Rudi, Lorenzo Rosasco
Published in: International Conference of Machine Learning, 2022
Publisher: ICML

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

Author(s): Vivien Cabannes, Loucas Pillaud-Vivien, Francis Bach, Alessandro Rudi
Published in: NeurIPS, 2021
Publisher: NeurIPS

Other (8)

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

Author(s): Adrien Vacher, Boris Muzellec, Alessandro Rudi, Francis Bach, Francois-Xavier Vialard
Published in: 2021
Publisher: Arxiv

A Note on Optimizing Distributions using Kernel Mean Embeddings

Author(s): Muzellec, Boris; Bach, Francis; Rudi, Alessandro
Published in: https://hal.archives-ouvertes.fr/hal-03454259, 2021
Publisher: HAL
DOI: 10.48550/arxiv.2106.09994

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

Author(s): Francis Bach, Alessandro Rudi
Published in: 2022
Publisher: Arxiv

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

Author(s): Boris Muzellec, Adrien Vacher, Francis Bach, François-Xavier Vialard, Alessandro Rudi
Published in: 2022
Publisher: Arxiv

Finding Global Minima via Kernel Approximations

Author(s): Alessandro Rudi, Ulysse Marteau-Ferey, Francis Bach
Published in: 2021
Publisher: Arxiv

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

Author(s): Boris Muzellec, Francis Bach, Alessandro Rudi
Published in: 2022
Publisher: Arxiv

Infinite-Dimensional Sums-of-Squares for Optimal Control

Author(s): Eloïse Berthier, Justin Carpentier, Alessandro Rudi, Francis Bach
Published in: 2021
Publisher: Arxiv

Second order conditions to decompose smooth functions as sums of squares

Author(s): Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi
Published in: 2022
Publisher: Arxix

Peer reviewed articles (1)

Vector-Valued Least-Squares Regression under Output Regularity Assumptions

Author(s): Luc Brogat-Motte, Alessandro Rudi, Céline Brouard, Juho Rousu, Florence d'Alché-Buc
Published in: Journal of Machine Learning Research, Issue Volume 23, 2022, ISSN 1533-7928
Publisher: JMLR