Large-Scale Learning with Deep Kernel Machines

Informazioni relative al progetto

SOLARIS

ID dell’accordo di sovvenzione: 714381

DOI

10.3030/714381

Progetto chiuso

Data della firma CE 28 Novembre 2016

Data di avvio 1 Marzo 2017

Data di completamento 28 Febbraio 2022

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 498 465,00

Contributo UE

€ 1 498 465,00

Coordinato da

INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET AUTOMATIQUE
France

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Conference proceedings (29)

The spectral bias of polynomial neural networks

Autori: M. Choraria, L. T. Dadi, G. Chrysos, J. Mairal and V. Cevher
Pubblicato in: International Conference on Learning Representations (ICLR), 2022
Editore: ICLR

Self-Supervised Models are Continual Learners

Autori: E. Fini, V. G. Turrisi da Costa, X. Alameda-Pineda, E. Ricci, K. Alahari and J. Mairal
Pubblicato in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Editore: IEEE

Fully Trainable and Interpretable Non-local Sparse Models for Image Restoration

Autori: Bruno Lecouat, Jean Ponce, Julien Mairal
Pubblicato in: Computer Vision – ECCV 2020 - 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXII, Numero 12367, 2020, Pagina/e 238-254, ISBN 978-3-030-58541-9
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-58542-6_15

A Generic Acceleration Framework for Stochastic Composite Optimization

Autori: Kulunchakov, Andrei; Mairal, Julien
Pubblicato in: NeurIPS 2019 - Thirty-third Conference Neural Information Processing Systems, Dec 2019, Vancouver, Canada. pp.12556-12567, 2019
Editore: Neurips

A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration

Autori: Theo Bodrito; Jocelyn Chanussot; Julien Mairal
Pubblicato in: Adv. Neural Information Processing Systems (NeurIPS), 2021
Editore: NeurIPS

Recurrent Kernel Networks

Autori: Chen, Dexiong; Jacob, Laurent; Mairal, Julien
Pubblicato in: NeurIPS 2019 - Neural Information Processing Systems, 2019
Editore: NeurIPS

Designing and Learning Trainable Priors with Non-Cooperative Games

Autori: Lecouat, Bruno; Ponce, Jean; Mairal, Julien
Pubblicato in: Adv. Neural Information Processing Systems (NeurIPS), 2020
Editore: NeurIPS

An Optimal Transport Kernel for Feature Aggregation and its Relationship to Attention

Autori: Mialon, Grégoire; Chen, Dexiong; D'Aspremont, Alexandre; Mairal, Julien
Pubblicato in: ICLR 2021 - International Conference on Learning Representations, 2021
Editore: ICLR

Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions

Autori: Mialon, Grégoire; D'Aspremont, Alexandre; Mairal, Julien
Pubblicato in: AISTATS 2020 - 23rd International Conference on Artificial Intelligence and Statistics, 2020
Editore: PMLR

Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts

Autori: Lecouat, Bruno; Ponce, Jean; Mairal, Julien
Pubblicato in: International Conference on Computer Vision (ICCV), 2021
Editore: IEEE
DOI: 10.1109/iccv48922.2021.00237

On the Inductive Bias of Neural Tangent Kernels

Autori: Bietti, Alberto; Mairal, Julien
Pubblicato in: NeurIPS 2019 - Thirty-third Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. pp.12873-12884, 2019
Editore: Neurips

Catalyst for Gradient-based Nonconvex Optimization

Autori: Paquette , Courtney; Lin , Hongzhou; Drusvyatskiy , Dmitriy; Mairal , Julien; Harchaoui , Zaid
Pubblicato in: AISTATS 2018 - 21st International Conference on Artificial Intelligence and Statistics, Apr 2018, Lanzarote, Spain. pp.1-10, 2018
Editore: PMLR

Learning Neural Representations of Human Cognition across Many fMRI Studies

Autori: Mensch, Arthur; Mairal, Julien; Bzdok, Danilo; Thirion, Bertrand; Varoquaux, Gaël
Pubblicato in: NIPS 2017 - Advances in Neural Information Processing Systems, 2017
Editore: NIPS proceedings

Invariance and Stability of Deep Convolutional Representations

Autori: Bietti , Alberto; Mairal , Julien
Pubblicato in: NIPS 2017 - 31st Conference on Advances in Neural Information Processing Systems, 2017
Editore: NIPS Proceedings

BlitzNet: A Real-Time Deep Network for Scene Understanding

Autori: Nikita Dvornik, Konstantin Shmelkok, Julien Mairal, Cordelia Schmid
Pubblicato in: ICCV 2017 - International Conference on Computer Vision, 2017
Editore: IEEE

Modeling Visual Context is Key to Augmenting Object Detection Datasets

Autori: Dvornik , Nikita; Mairal , Julien; Schmid , Cordelia
Pubblicato in: ECCV 2018 - European Conference on Computer Vision, 2018
Editore: Springer

Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure

Autori: Bietti , Alberto; Mairal , Julien
Pubblicato in: NIPS 2017 - Advances in Neural Information Processing Systems, 2017
Editore: NIPS proceedings

Unsupervised Learning of Artistic Styles with Archetypal Style Analysis

Autori: Wynen, Daan; Schmid, Cordelia; Mairal, Julien
Pubblicato in: NIPS 2018 - Advances in Neural Information Processing Systems, 2018
Editore: NIPS proceedings

A Kernel Perspective for Regularizing Deep Neural Networks

Autori: Bietti, Alberto; Mialon, Grégoire; Chen, Dexiong; Mairal, Julien
Pubblicato in: International Conference on Machine Learning (ICML), Numero 97, 2019, ISSN 2640-3498
Editore: PMLR

Diversity with Cooperation: Ensemble Methods for Few-Shot Classification

Autori: Dvornik, Nikita; Schmid, Cordelia; Mairal, Julien
Pubblicato in: International Conference on Computer Vision (ICCV), 2019
Editore: IEEE

Estimate Sequences for Variance-Reduced Stochastic Composite Optimization

Autori: Kulunchakov, Andrei; Mairal, Julien
Pubblicato in: International Conference on Machine Learning (ICML), Numero 97, 2019
Editore: PMLR

Unsupervised Pre-Training of Image Features on Non-Curated Data

Autori: Caron, Mathilde; Bojanowski, Piotr; Mairal, Julien; Joulin, Armand
Pubblicato in: International Conference on Computer Vision (ICCV), 2019
Editore: IEEE

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

Autori: Caron, Mathilde; Misra, Ishan; Mairal, Julien; Goyal, Priya; Bojanowski, Piotr; Joulin, Armand
Pubblicato in: NeurIPS 2020 - Neural Information Processing Systems, 2020
Editore: PMLR

Convolutional Kernel Networks for Graph-Structured Data

Autori: Chen, Dexiong; Jacob, Laurent; Mairal, Julien
Pubblicato in: ICML 2020 - 37th International Conference on Machine Learning, 2020
Editore: PMLR

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

Autori: Beugnot, Gaspard; Mairal, Julien; Rudi, Alessandro
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2021
Editore: NeurIPS

Efficient Kernel UCB for Contextual Bandits

Autori: H. Zenati, A. Bietti, E. Diemert, J. Mairal, M. Martin and P. Gaillard
Pubblicato in: International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
Editore: AISTATS

Selecting Relevant Features from a Multi-domain Representation for Few-Shot Classification

Autori: Nikita Dvornik, Cordelia Schmid, Julien Mairal
Pubblicato in: Computer Vision – ECCV 2020 - 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part X, Numero 12355, 2020, Pagina/e 769-786, ISBN 978-3-030-58606-5
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-58607-2_45

Emerging Properties in Self-Supervised Vision Transformers

Autori: Caron, Mathilde; Touvron, Hugo; Misra, Ishan; Jegou, Hervé; Mairal, Julien; Bojanowski, Piotr; Joulin, Armand
Pubblicato in: International Conference on Computer Vision (ICCV), 2021
Editore: IEEE
DOI: 10.1109/iccv48922.2021.00951

Amortized Implicit Differentiation for Stochastic Bilevel Optimization

Autori: M. Arbel and J. Mairal
Pubblicato in: International Conference on Learning Representations (ICLR), 2022
Editore: ICLR

Peer reviewed articles (9)

Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise

Autori: Kulunchakov, Andrei; Mairal, Julien
Pubblicato in: Journal of Machine Learning Research (JMLR), Numero 21, 2020, ISSN 1532-4435
Editore: MIT Press

Extracting representations of cognition across neuroimaging studies improves brain decoding

Autori: Arthur Mensch, Julien Mairal, Bertrand Thirion, Gaël Varoquaux
Pubblicato in: PLOS Computational Biology, Numero 17/5, 2021, Pagina/e e1008795, ISSN 1553-734X
Editore: Public Library of Science
DOI: 10.1371/journal.pcbi.1008795

Stochastic Subsampling for Factorizing Huge Matrices

Autori: Arthur Mensch, Julien Mairal, Bertrand Thirion, Gael Varoquaux
Pubblicato in: IEEE Transactions on Signal Processing, Numero 66/1, 2018, Pagina/e 113-128, ISSN 1053-587X
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TSP.2017.2752697

Loter: A Software Package to Infer Local Ancestry for a Wide Range of Species

Autori: Thomas Dias-Alves, Julien Mairal, Michael G B Blum
Pubblicato in: Molecular Biology and Evolution, Numero 35/9, 2018, Pagina/e 2318-2326, ISSN 0737-4038
Editore: Oxford University Press
DOI: 10.1093/molbev/msy126

Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice

Autori: Lin , Hongzhou; Mairal , Julien; Harchaoui , Zaid
Pubblicato in: Journal of Machine Learning Research, Numero 18, 2018, ISSN 1532-4435
Editore: MIT Press

Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations

Autori: Bietti, Alberto; Mairal, Julien
Pubblicato in: Journal of Machine Learning Research, Numero 20, 2019, ISSN 1532-4435
Editore: MIT Press

An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration

Autori: Hongzhou Lin, Julien Mairal, Zaid Harchaoui
Pubblicato in: SIAM Journal on Optimization, Numero 29/2, 2019, Pagina/e 1408-1443, ISSN 1052-6234
Editore: Society for Industrial and Applied Mathematics
DOI: 10.1137/17M1125157

Biological sequence modeling with convolutional kernel networks

Autori: Dexiong Chen, Laurent Jacob, Julien Mairal
Pubblicato in: Bioinformatics, 2019, ISSN 1367-4803
Editore: Oxford University Press
DOI: 10.1093/bioinformatics/btz094

On the Importance of Visual Context for Data Augmentation in Scene Understanding

Autori: Nikita Dvornik, Julien Mairal, Cordelia Schmid
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 43/6, 2021, Pagina/e 2014-2028, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2019.2961896