Opendata, web and dolomites

SOLARIS SIGNED

Large-Scale Learning with Deep Kernel Machines

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

Project "SOLARIS" data sheet

The following table provides information about the project.

Coordinator
INSTITUT NATIONAL DE RECHERCHE ENINFORMATIQUE ET AUTOMATIQUE 

Organization address
address: DOMAINE DE VOLUCEAU ROCQUENCOURT
city: LE CHESNAY CEDEX
postcode: 78153
website: www.inria.fr

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country France [FR]
 Total cost 1˙498˙465 €
 EC max contribution 1˙498˙465 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2016-STG
 Funding Scheme ERC-STG
 Starting year 2017
 Duration (year-month-day) from 2017-03-01   to  2022-02-28

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    INSTITUT NATIONAL DE RECHERCHE ENINFORMATIQUE ET AUTOMATIQUE FR (LE CHESNAY CEDEX) coordinator 1˙498˙465.00

Map

 Project objective

Machine learning has become a key part of scientific fields that produce a massive amount of data and that are in dire need of scalable tools to automatically make sense of it. Unfortunately, classical statistical modeling has often become impractical due to recent shifts in the amount of data to process, and in the high complexity and large size of models that are able to take advantage of massive data. The promise of SOLARIS is to invent a new generation of machine learning models that fulfill the current needs of large-scale data analysis: high scalability, ability to deal with huge-dimensional models, fast learning, easiness of use, and adaptivity to various data structures. To achieve the expected breakthroughs, our angle of attack consists of novel optimization techniques for solving large-scale problems and a new learning paradigm called deep kernel machine. This paradigm marries two schools of thought that have been considered so far to have little overlap: kernel methods and deep learning. The former is associated with a well-understood theory and methodology but lacks scalability, whereas the latter has obtained significant success on large-scale prediction problems, notably in computer vision. Deep kernel machines will lead to theoretical and practical breakthroughs in machine learning and related fields. For instance, convolutional neural networks were invented more than two decades ago and are today’s state of the art for image classification. Yet, theoretical foundations and principled methodology for these deep networks are nowhere to be found. The project will address such fundamental issues, and its results are expected to make deep networks simpler to design, easier to use, and faster to train. It will also leverage the ability of kernels to model invariance and work with a large class of structured data such as graphs and sequences, leading to a broad scope of applications with potentially groundbreaking advances in diverse scientific fields.

 Publications

year authors and title journal last update
List of publications.
2019 Bietti, Alberto; Mialon, Grégoire; Chen, Dexiong; Mairal, Julien
A Kernel Perspective for Regularizing Deep Neural Networks
published pages: , ISSN: 2640-3498, DOI:
International Conference on Machine Learning (ICML) 97 2019-09-17
2019 Caron, Mathilde; Bojanowski, Piotr; Mairal, Julien; Joulin, Armand
Unsupervised Pre-Training of Image Features on Non-Curated Data
published pages: , ISSN: , DOI:
International Conference on Computer Vision (ICCV) 2019-09-17
2019 Kulunchakov, Andrei; Mairal, Julien
Estimate Sequences for Variance-Reduced Stochastic Composite Optimization
published pages: , ISSN: , DOI:
International Conference on Machine Learning (ICML) 97 2019-09-17
2019 Dvornik, Nikita; Schmid, Cordelia; Mairal, Julien
Diversity with Cooperation: Ensemble Methods for Few-Shot Classification
published pages: , ISSN: , DOI:
International Conference on Computer Vision (ICCV) 2019-09-17
2019 Dexiong Chen, Laurent Jacob, Julien Mairal
Biological sequence modeling with convolutional kernel networks
published pages: , ISSN: 1367-4803, DOI: 10.1093/bioinformatics/btz094
Bioinformatics 2019-09-17
2019 Hongzhou Lin, Julien Mairal, Zaid Harchaoui
An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration
published pages: 1408-1443, ISSN: 1052-6234, DOI: 10.1137/17M1125157
SIAM Journal on Optimization 29/2 2019-09-17
2019 Bietti, Alberto; Mairal, Julien
Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations
published pages: , ISSN: 1532-4435, DOI:
Journal of Machine Learning Research 20 2019-09-17
2017 Bietti , Alberto; Mairal , Julien
Invariance and Stability of Deep Convolutional Representations
published pages: , ISSN: , DOI:
NIPS 2017 - 31st Conference on Advances in Neural Information Processing Systems 2019-06-13
2018 Paquette , Courtney; Lin , Hongzhou; Drusvyatskiy , Dmitriy; Mairal , Julien; Harchaoui , Zaid
Catalyst for Gradient-based Nonconvex Optimization
published pages: , ISSN: , DOI:
AISTATS 2018 - 21st International Conference on Artificial Intelligence and Statistics, Apr 2018, Lanzarote, Spain. pp.1-10 2019-06-13
2018 Thomas Dias-Alves, Julien Mairal, Michael G B Blum
Loter: A Software Package to Infer Local Ancestry for a Wide Range of Species
published pages: 2318-2326, ISSN: 0737-4038, DOI: 10.1093/molbev/msy126
Molecular Biology and Evolution 35/9 2019-06-13
2017 Mensch, Arthur; Mairal, Julien; Bzdok, Danilo; Thirion, Bertrand; Varoquaux, Gaël
Learning Neural Representations of Human Cognition across Many fMRI Studies
published pages: , ISSN: , DOI:
NIPS 2017 - Advances in Neural Information Processing Systems 2019-06-13
2018 Wynen, Daan; Schmid, Cordelia; Mairal, Julien
Unsupervised Learning of Artistic Styles with Archetypal Style Analysis
published pages: , ISSN: , DOI:
NIPS 2018 - Advances in Neural Information Processing Systems 2019-06-13
2017 Nikita Dvornik, Konstantin Shmelkok, Julien Mairal, Cordelia Schmid
BlitzNet: A Real-Time Deep Network for Scene Understanding
published pages: , ISSN: , DOI:
ICCV 2017 - International Conference on Computer Vision 2019-06-13
2018 Dvornik , Nikita; Mairal , Julien; Schmid , Cordelia
Modeling Visual Context is Key to Augmenting Object Detection Datasets
published pages: , ISSN: , DOI:
ECCV 2018 - European Conference on Computer Vision 2019-06-13
2017 Bietti , Alberto; Mairal , Julien
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure
published pages: , ISSN: , DOI:
NIPS 2017 - Advances in Neural Information Processing Systems 2019-06-13
2018 Lin , Hongzhou; Mairal , Julien; Harchaoui , Zaid
Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice
published pages: , ISSN: 1532-4435, DOI:
Journal of Machine Learning Research 18 2019-06-13

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "SOLARIS" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "SOLARIS" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)

InsideChromatin (2019)

Towards Realistic Modelling of Nucleosome Organization Inside Functional Chromatin Domains

Read More  

PROGRESS (2019)

The Enemy of the Good: Towards a Theory of Moral Progress

Read More  

SuperH (2019)

Discovery and Characterization of Hydrogen-Based High-Temperature Superconductors

Read More