New paradigms for latent factor estimation

Project Information

FACTORY

Grant agreement ID: 681839

DOI

10.3030/681839

Project closed

EC signature date 26 April 2016

Start date 1 September 2016

End date 31 August 2022

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost

€ 1 931 776,25

EU contribution

€ 1 931 776,25

Coordinated by

CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRS
France

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Peer reviewed articles (17)

A Comparative Study of Gamma Markov Chains for Temporal Non-Negative Matrix Factorization

Author(s): Louis Filstroff; Olivier Gouvert; Cédric Févotte; Olivier Cappé
Published in: IEEE Transactions on Signal Processing, 2021, ISSN 1053-587X
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tsp.2021.3060000

Expanding boundaries of Gap Safe screening

Author(s): Dantas, Cassio,; Soubies, Emmanuel; Févotte, Cédric
Published in: Journal of Machine Learning Research, 2021, ISSN 1533-7928
Publisher: Microtome Publishing

Multiplicative Updates for NMF with $\beta$-Divergences under Disjoint Equality Constraints

Author(s): Valentin Leplat; Nicolas Gillis; Jerome Idier
Published in: Signal Processing, 2022, ISSN 0165-1684
Publisher: Elsevier BV
DOI: 10.1137/20m1377278

Neural content-aware collaborative filtering for cold-start music recommendation

Author(s): Magron, Paul; Févotte, Cédric
Published in: Data Mining and Knowledge Discovery, 2022, ISSN 1384-5810
Publisher: Kluwer Academic Publishers
DOI: 10.1007/s10618-022-00859-8

A Majorization-Minimization Algorithm for Nonnegative Binary Matrix Factorization

Author(s): Paul Magron; Cedric Fevotte
Published in: IEEE Signal Processing Letters, 2022, ISSN 1070-9908
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lsp.2022.3187368

Bayesian mean-parameterized nonnegative binary matrix factorization

Author(s): Alberto Lumbreras; Louis Filstroff; Cédric Févotte
Published in: Data Mining and Knowledge Discovery volume, 2020, ISSN 1384-5810
Publisher: Kluwer Academic Publishers
DOI: 10.1007/s10618-020-00712-w

Negative binomial matrix factorization

Author(s): O. Gouvert, T. Oberlin and C. Févotte
Published in: IEEE Signal Processing Letters, 2020, ISSN 1070-9908
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lsp.2020.2991613

Positive Semidefinite Matrix Factorization: A Connection With Phase Retrieval and Affine Rank Minimization

Author(s): Dana Lahat; Yanbin Lang; Vincent Y. F. Tan; Cédric Févotte
Published in: IEEE Transactions on Signal Processing, 2021, ISSN 1053-587X
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tsp.2021.3071293

Estimation with low-rank time-frequency synthesis models

Author(s): C. Févotte and M. Kowalski
Published in: IEEE Transactions on Signal Processing, 2018, ISSN 1053-587X
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tsp.2018.2844159

Factor analysis of dynamic PET images: beyond Gaussian noise

Author(s): Y. C. Cavalcanti, T. Oberlin, N. Dobigeon, C. Févotte, S. Stute, and C. Tauber
Published in: IEEE Transactions on Medical Imaging, 2019, ISSN 0278-0062
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tmi.2019.2906828

Leveraging joint-diagonalization in transform-learning NMF

Author(s): S. Zhang, E. Soubies and C. Févotte
Published in: IEEE Transactions on Signal Processing, 2022, ISSN 1053-587X
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tsp.2022.3188177

On the identifiability of transform learning for non-negative matrix factorization

Author(s): S. Zhang, E. Soubies and C. Févotte
Published in: IEEE Signal Processing Letters, 2020, ISSN 1070-9908
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lsp.2020.3020431

Adversarially-trained nonnegative matrix factorization

Author(s): T. Cai, V.Y.F. Tan and C. Févotte
Published in: IEEE Signal Processing Letters, 2021, ISSN 1070-9908
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lsp.2021.3092231

An Inertial Newton Algorithm for Deep Learning

Author(s): Castera, Camille; Bolte, Jérôme; Févotte, Cédric; Pauwels, Edouard
Published in: Journal of Machine Learning Research, 2021, ISSN 1533-7928
Publisher: Microtome Publishing
DOI: 10.48550/arxiv.1905.12278

Learning the proximity operator in unfolded ADMM for phase retrieval

Author(s): P.-H. Vial, P. Magron, T. Oberlin and C. Févotte
Published in: IEEE Signal Processing Letters, 2022, ISSN 1070-9908
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lsp.2022.3189275

Second-order step-size tuning of SGD for non-convex optimization

Author(s): Camille Castera; Jérôme Bolte; Cédric Févotte; Edouard Pauwels
Published in: Neural Processing Letters, 2022, ISSN 1370-4621
Publisher: Kluwer Academic Publishers
DOI: 10.1007/s11063-021-10705-5

Phase retrieval with Bregman divergences and application to audio signal recovery

Author(s): P.-H. Vial, P. Magron, T. Oberlin and C. Févotte
Published in: IEEE Journal of Selected Topics in Signal Processing, 2021, ISSN 1932-4553
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/jstsp.2021.3051870

Conference proceedings (18)

Unbalanced optimal transport through non-negative penalized linear regression

Author(s): L. Chapel, R. Flamary, H. Wu, C. Févotte and G. Gasso
Published in: Advances in Neural Information Processing Systems (NIPS), 2021
Publisher: NIPS Foudation

An inertial Newton algorithm for deep learning

Author(s): C. Castera, J. Bolte, C. Févotte & E. Pauwels
Published in: "Proc. NeurIPS Workshop ``Beyond First Order Methods in ML""", 2019
Publisher: -

Positive Semidefinite Matrix Factorization: A Link to Phase Retrieval And A Block Gradient Algorithm

Author(s): Dana Lahat; Cédric Févotte
Published in: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
Publisher: IEEE
DOI: 10.1109/icassp40776.2020.9053938

Phase recovery with Bregman divergences for audio source separation

Author(s): P. Magron, P.-H. Vial, T. Oberlin & C. Févotte
Published in: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
Publisher: IEEE

Safe screening for sparse regression with the Kullback-Leibler divergence

Author(s): C. Dantas, E. Soubies & C. Févotte
Published in: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
Publisher: IEEE

Recommendation from Raw Data with Adaptive Compound Poisson Factorization

Author(s): Gouvert, Olivier; Oberlin, Thomas; Févotte, Cédric
Published in: Proc. Conference on Uncertainty in Artificial Intelligence, 2019
Publisher: PMLR

Leveraging the structure of musical preference in content-aware music recommendation

Author(s): P. Magron and C. Févotte
Published in: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
Publisher: IEEE

Optimal spectral transportation with application to music transcription

Author(s): R. Flamary, C. Févotte, N. Courty, and V. Emiya
Published in: Advances in Neural Information Processing Systems (NIPS), 2016
Publisher: NIPS Foundation

Nonnegative matrix factorization with transform learning

Author(s): D. Fagot, H. Wendt, and C. Févotte
Published in: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
Publisher: IEEE

A quasi-Newton algorithm on the orthogonal manifold for NMF with transform learning

Author(s): P. Ablin, D. Fagot, H. Wendt, A. Gramfort, and C. Févotte
Published in: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
Publisher: IEEE

Unmixing dynamic PET images: Combining spatial heterogeneity and non-gaussian noise

Author(s): Y. C. Cavalcanti, T. Oberlin, N. Dobigeon, C. Févotte, S. Stute, and C. Tauber
Published in: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
Publisher: IEEE

Majorization-minimization algorithms for convolutive NMF with the beta-divergence

Author(s): D. Fagot, H. Wendt, C. Févotte, and P. Smaragdis
Published in: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
Publisher: IEEE

Closed-form marginal likelihood in Gamma-Poisson matrix factorization

Author(s): L. Filstroff, A. Lumbreras, and C. Févotte
Published in: Proc. International Conference on Machine Learning (ICML), 2018
Publisher: PMLR

Matrix co-factorization for cold-start recommendation

Author(s): O. Gouvert, T. Oberlin, and C. Févotte
Published in: Proc. International Society for Music Information Retrieval Conference (ISMIR), 2018
Publisher: ISMIR

Jacobi algorithm for nonnegative matrix factorization with transform learning

Author(s): H. Wendt, D. Fagot, and C. Févotte
Published in: Proc. European Signal Processing Conference (EUSIPCO), 2018
Publisher: EURASIP

A ranking model motivated by nonnegative matrix factorization with applications to tennis tournaments

Author(s): R. Xia, V. Y. F. Tan, L. Filstroff and C. Févotte
Published in: Proc. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), 2019
Publisher: Springer
DOI: 10.1007/978-3-030-46133-1_12

Positive Semidefinite Matrix Factorization Based on Truncated Wirtinger Flow

Author(s): Dana Lahat; Cédric Févotte
Published in: Proc. European Signal Processing Conference (EUSIPCO), 2020
Publisher: EURASIP
DOI: 10.23919/eusipco47968.2020.9287560

Ordinal non-negative matrix factorization for recommendation

Author(s): O. Gouvert, T. Oberlin & C. Févotte
Published in: Proc. International Conference on Machine Learning (ICML), 2020
Publisher: IEEE

Other (4)

Majorization-minimization for sparse nonnegative matrix factorization with the beta-divergence

Author(s): A. Marmin, J.H. de M. Goulart & C. Févotte
Published in: arXiv, 2022
Publisher: arXiv

Negative binomial matrix factorization for recommender systems

Author(s): O. Gouvert, T. Oberlin, and C. Févotte
Published in: arXiv, 2018
Publisher: arXiv

Algorithms for audio inpainting based on probabilistic nonnegative matrix factorization

Author(s): O. Mokrý, P. Magron, T. Oberlin & C. Févotte
Published in: arXiv, 2022
Publisher: arXiv

Joint majorization-minimization for nonnegative matrix factorization with the beta-divergence

Author(s): A. Marmin, J.H. de M. Goulart & C. Févotte
Published in: arXiv, 2021
Publisher: arXiv

Book chapters (3)

Temporal extensions of nonnegative matrix factorization

Author(s): C. Févotte, P. Smaragdis, N. Mohammadiha, and G. Mysore
Published in: Audio Source Separation and Speech Enhancement, 2018
Publisher: Wiley

An introduction to multichannel NMF for audio source separation

Author(s): A. Ozerov, C. Févotte, and E. Vincent
Published in: Audio Source Separation, 2018
Publisher: Springer

Single-channel audio source separation with NMF: divergences, constraints and algorithms

Author(s): C. Févotte, E. Vincent, and A. Ozerov
Published in: Audio Source Separation, 2018
Publisher: Springer