Opendata, web and dolomites

SEQUOIA SIGNED

Robust algorithms for learning from modern data

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

Project "SEQUOIA" 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˙998˙750 €
 EC max contribution 1˙998˙750 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2016-COG
 Funding Scheme ERC-COG
 Starting year 2017
 Duration (year-month-day) from 2017-09-01   to  2022-08-31

 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˙998˙750.00

Map

 Project objective

Machine learning is needed and used everywhere, from science to industry, with a growing impact on many disciplines. While first successes were due at least in part to simple supervised learning algorithms used primarily as black boxes on medium-scale problems, modern data pose new challenges. Scalability is an important issue of course: with large amounts of data, many current problems far exceed the capabilities of existing algorithms despite sophisticated computing architectures. But beyond this, the core classical model of supervised machine learning, with the usual assumptions of independent and identically distributed data, or well-defined features, outputs and loss functions, has reached its theoretical and practical limits.

Given this new setting, existing optimization-based algorithms are not adapted. The main objective of this proposal is to push the frontiers of supervised machine learning, in terms of (a) scalability to data with massive numbers of observations, features, and tasks, (b) adaptability to modern computing environments, in particular for parallel and distributed processing, (c) provable adaptivity and robustness to problem and hardware specifications, and (d) robustness to non-convexities inherent in machine learning problems.

To achieve the expected breakthroughs, we will design a novel generation of learning algorithms amenable to a tight convergence analysis with realistic assumptions and efficient implementations. They will help transition machine learning algorithms towards the same wide-spread robust use as numerical linear algebra libraries. Outcomes of the research described in this proposal will include algorithms that come with strong convergence guarantees and are well-tested on real-life benchmarks coming from computer vision, bioinformatics, audio processing and natural language processing. For both distributed and non-distributed settings, we will release open-source software, adapted to widely available computing platforms.

 Publications

year authors and title journal last update
List of publications.
2018 Pauwels , Edouard; Bach , Francis; Vert , Jean-Philippe
Relating Leverage Scores and Density using Regularized Christoffel Functions
published pages: , ISSN: , DOI:
Advances in NIPS 2019-06-06
2018 Chizat , Lenaic; Bach , Francis
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
published pages: , ISSN: , DOI:
Advances in NIPS 1 2019-06-06
2019 Adrien Taylor, Francis Bach
Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions
published pages: , ISSN: , DOI:
Proceedings COLT 2019-06-06
2019 Alex Nowak-Ville, Alessandro Rudi, Francis Bach
Sharp Analysis of Learning with Discrete Losses
published pages: , ISSN: , DOI:
Proceedings AISTATS 2019-06-06
2018 Rudi , Alessandro; Calandriello , Daniele; Carratino , Luigi; Rosasco , Lorenzo
On Fast Leverage Score Sampling and Optimal Learning
published pages: , ISSN: , DOI:
Advances in NIPS 28 2019-06-06
2018 Pillaud-Vivien, Loucas; Rudi, Alessandro; Bach, Francis
Exponential convergence of testing error for stochastic gradient methods
published pages: , ISSN: , DOI:
Proceedings of COLT 5 2019-06-06
2018 Loucas Pillaud-Vivien, Alessandro Rudi, Francis Bach
Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes
published pages: , ISSN: , DOI:
Advances in Neural Information Processing Systems (NIPS) 2019-06-06

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "SEQUOIA" 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 "SEQUOIA" are provided by the European Opendata Portal: CORDIS opendata.

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

DISINTEGRATION (2019)

The Mass Politics of Disintegration

Read More  

PROGRESS (2019)

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

Read More  

Neurovulnerability (2019)

Molecular mechanisms underlying selective neuronal death in motor neuron diseases

Read More