Information Theory beyond Communications: Distributed Representations and Deep Learning

Informacje na temat projektu

STRUDEL

Identyfikator umowy o grant: 797805

DOI

10.3030/797805

Projekt został zamknięty

Data podpisania przez KE 5 Kwietnia 2018

Data rozpoczęcia 1 Września 2018

Data zakończenia 31 Sierpnia 2020

Finansowanie w ramach

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Koszt całkowity

€ 171 349,20

Wkład UE

€ 171 349,20

Koordynowany przez

CENTRALESUPELEC
France

CORDIS oferuje możliwość skorzystania z odnośników do publicznie dostępnych publikacji i rezultatów projektów realizowanych w ramach programów ramowych HORYZONT.

Odnośniki do rezultatów i publikacji związanych z poszczególnymi projektami 7PR, a także odnośniki do niektórych konkretnych kategorii wyników, takich jak zbiory danych i oprogramowanie, są dynamicznie pobierane z systemu OpenAIRE .

Publikacje

Conference proceedings (13)

Detecting Covariate Shift with Black Box Predictors

Autorzy: Florence Alberge, Clement Feutry, Pierre Duhamel, Pablo Piantanida
Opublikowane w: 2019 26th International Conference on Telecommunications (ICT), 2019, Strona(/y) 324-329, ISBN 978-1-7281-0273-3
Wydawca: IEEE
DOI: 10.1109/ict.2019.8798827

Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release

Autorzy: Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida, Fabrice Labeau
Opublikowane w: 2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 2019, Strona(/y) 1-7, ISBN 978-1-5386-8099-5
Wydawca: IEEE
DOI: 10.1109/smartgridcomm.2019.8909813

Privacy-Preserving Synthetic Smart Meters Data

Autorzy: Ganesh Del Grosso, Georg Pichler, Pablo Piantanida
Opublikowane w: 2021 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2021, Strona(/y) 1-5, ISBN 978-1-7281-8897-3
Wydawca: IEEE
DOI: 10.1109/isgt49243.2021.9372157

Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?

Autorzy: Malik Boudiaf, Hoel Kervadec, Ziko Imtiaz Masud, Pablo Piantanida, Ismail Ben Ayed, Jose Dolz
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, Strona(/y) 13979-13988, ISBN 978-1-6654-4509-2
Wydawca: IEEE
DOI: 10.1109/cvpr46437.2021.01376

A Differential Entropy Estimator for Training Neural Networks

Autorzy: Georg Pichler, Pierre Jean A. Colombo, Malik Boudiaf, Günther Koliander, Pablo Piantanida
Opublikowane w: International Conference on Machine Learning, Numer 162, 2022, Strona(/y) 17691-17715
Wydawca: PMLR

DOCTOR: A Simple Method for Detecting Misclassification Errors

Autorzy: Federica Granese, Marco Romanelli, Daniele Gorla, Catuscia Palamidessi, Pablo Piantanida
Opublikowane w: Advances in Neural Information Processing Systems, Numer 34, 2021, Strona(/y) 5669-5681, ISSN 1049-5258
Wydawca: Curran Associates, Inc.
DOI: 10.48550/arxiv.2106.02395

A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations

Autorzy: Pierre Colombo, Pablo Piantanida, Chloé Clavel
Opublikowane w: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021, Strona(/y) 6539–6550
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2021.acl-long.511

Transductive Information Maximization For Few-Shot Learning

Autorzy: Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony, Jose Dolz, Pablo Piantanida,Ismail Ben Ayed
Opublikowane w: Conference on Neural Information Processing Systems, Numer 33, 2020, ISBN 9781713829546
Wydawca: Curran Associates, Inc.

Privacy-Cost Management in Smart Meters Using Deep Reinforcement Learning

Autorzy: Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida, Fabrice Labeau
Opublikowane w: 2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe), 2020, Strona(/y) 929-933, ISBN 978-1-7281-7100-5
Wydawca: IEEE
DOI: 10.1109/isgt-europe47291.2020.9248831

Estimating g-leakage via machine learning

Autorzy: K. Chatzikokolakis, C. Palamidessi, P. Piantanida, and M. Romanelli
Opublikowane w: ACM Conference on Computer and Communications Security (CCS), 2020
Wydawca: ACM
DOI: 10.1145/3372297.3423363

On the Impact of Side Information on Smart Meter Privacy-Preserving Methods

Autorzy: Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida, Fabrice Labeau
Opublikowane w: 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 2020, Strona(/y) 1-6, ISBN 978-1-7281-6127-3
Wydawca: IEEE
DOI: 10.1109/smartgridcomm47815.2020.9302948

Learning Semi-Supervised Anonymized Representations by Mutual Information

Autorzy: C. Feutry, P. Piantanida, P. Duhamel
Opublikowane w: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Strona(/y) 3467-3471, ISBN 978-1-5090-6631-5
Wydawca: IEEE
DOI: 10.1109/icassp40776.2020.9053379

On Direct Distribution Matching for Adapting Segmentation Networks SAVE

Autorzy: Pichler, Georg; Dolz, Jose; Ayed, Ismail Ben; Piantanida, Pablo
Opublikowane w: MIDL 2020 - Medical Imaging with Deep Learning Publications Manually add publicatio, Numer 3, 2020
Wydawca: PMLR
DOI: 10.48550/arXiv.1904.02657

Other (2)

Learning anonymized representations with adversarial neural networks

Autorzy: C. Feutry, P. Piantanida, Y. Bengio, and P. Duhamel
Opublikowane w: Technical report, 2018
Wydawca: Online technical report

On the Estimation of Information Measures of Continuous Distributions

Autorzy: Georg Pichler, Pablo Piantanida, Günther Koliander
Opublikowane w: Technical report, 2020
Wydawca: Technical Report

Peer reviewed articles (10)

On Universal D-Semifaithful Coding for Memoryless Sources With Infinite Alphabets

Autorzy: Jorge F. Silva, Pablo Piantanida
Opublikowane w: IEEE Transactions on Information Theory, Numer Volume: 68, Numer: 4, 2022, Strona(/y) 1557-9654, ISSN 0018-9448
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tit.2021.3134891

Finite-Length Bounds on Hypothesis Testing Subject to Vanishing Type I Error Restrictions

Autorzy: Sebastian Espinosa, Jorge F. Silva, Pablo Piantanida
Opublikowane w: IEEE Signal Processing Letters, Numer 28, 2021, Strona(/y) 229-233, ISSN 1070-9908
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lsp.2021.3050381

Collaborative Information Bottleneck

Autorzy: Matias Vera, Leonardo Rey Vega, Pablo Piantanida
Opublikowane w: IEEE Transactions on Information Theory, Numer 65/2, 2019, Strona(/y) 787-815, ISSN 0018-9448
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tit.2018.2883295

The Role of Mutual Information in Variational Classifiers

Autorzy: Matias Vera, Leonardo Rey Vega, Pablo Piantanida
Opublikowane w: Under revision for publication in Machine Learning, 2023, ISSN 1532-4435
Wydawca: MIT Press
DOI: 10.1007/s10994-023-06337-6

Distributed information-theoretic clustering

Autorzy: Georg Pichler, Pablo Piantanida, Gerald Matz
Opublikowane w: Information and Inference: A Journal of the IMA, 2021, ISSN 2049-8772
Wydawca: Oxford University Press
DOI: 10.1093/imaiai/iaab007

Fundamental Limits of Decentralized Data Shuffling

Autorzy: Kai Wan, Daniela Tuninetti, Mingyue Ji, Giuseppe Caire, Pablo Piantanida
Opublikowane w: IEEE Transactions on Information Theory, Numer 66/6, 2020, Strona(/y) 3616-3637, ISSN 0018-9448
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tit.2020.2966197

On the Exponential Approximation of Type II Error Probability of Distributed Test of Independence

Autorzy: Espinosa, Sebastian; Silva, Jorge F.; Piantanida, Pablo
Opublikowane w: IEEE Transactions on Signal and Information Processing over Networks, 2021, Strona(/y) 777 - 790, ISSN 2373-776X
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tsipn.2021.3133192

Adversarial Robustness Via Fisher-Rao Regularization

Autorzy: Marine Picot, Francisco Messina, Malik Boudiaf, Fabrice Labeau, Ismail Ben Ayed, Pablo Piantanida
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numer vol. 45, no. 3, 2023, Strona(/y) 2698-2710, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2022.3174724

Privacy-Cost Management in Smart Meters with Mutual Information-Based Reinforcement Learning

Autorzy: M. Shateri, F. Messina, P. Piantanida, and F. Labeau
Opublikowane w: IEEE Internet of Things Journal, 2021, Strona(/y) 1 - 1, ISSN 2327-4662
Wydawca: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/jiot.2021.3128488

Real-Time Privacy-Preserving Data Release for Smart Meters

Autorzy: Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida, Fabrice Labeau
Opublikowane w: IEEE Transactions on Smart Grid, 2020, Strona(/y) 1-1, ISSN 1949-3053
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tsg.2020.3005634

Book chapters (2)

Information Bottleneck and Representation Learning

Autorzy: Pablo Piantanida, Leonardo Rey Vega
Opublikowane w: Information-Theoretic Methods in Data Science, 2021, Strona(/y) 330-358, ISBN 9781108616799
Wydawca: Cambridge University Press
DOI: 10.1017/9781108616799.012

A Unifying Mutual Information View of Metric Learning: Cross-Entropy vs. Pairwise Losses

Autorzy: Malik Boudiaf, Jérôme Rony, Imtiaz Masud Ziko, Eric Granger, Marco Pedersoli, Pablo Piantanida, Ismail Ben Ayed
Opublikowane w: Computer Vision – ECCV 2020 - 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VI, Numer 12351, 2020, Strona(/y) 548-564, ISBN 978-3-030-58538-9
Wydawca: Springer International Publishing
DOI: 10.1007/978-3-030-58539-6_33