Cédric Févotte


CNRS Research Director
Institut de Recherche en Informatique de Toulouse (IRIT)
Université de Toulouse


  • ICASSP tutorial Recent advances in nonnegative matrix factorization, with Vincent F. Tan, 2022. (slides)

  • Two experimental computer-generated movies presented at the video art festival Traverse, Toulouse, 2022.

  • Elevated to IEEE Fellow, for contributions to nonnegative matrix factorization, source separation, and spectral unmixing, 2022.

  • NeurIPS paper Unbalanced optimal transport through non-negative penalized linear regression, with Rémi Flamary, Laetitia Chapel, Haoran Wu and Gilles Gassio, 2021.

  • JMLR paper Expanding boundaries of Gap Safe screening, with Cassio Dantas and Emmanuel Soubies, 2021.

  • JMLR paper An inertial Newton algorithm for deep learning, with Camille Castera, Édouard Pauwels and Jérôme Bolte, 2021.


  • Principal investigator of European Research Council (ERC) project FACTORY (New paradigms for latent factor estimation)

  • Member of the Signal & Communications (SC) group of IRIT

  • Member of AOC, the machine learning group of Labex CIMI (Centre International de Mathématiques et Informatique de Toulouse)

  • Member of ANITI (Artificial and Natural Intelligence Toulouse Institute)

  • Member of IPAL (CNRS International Research Laboratory on Artificial Intelligence, Singapore)

  • Member of ELLIS (European Laboratory for Learning and Intelligent Systems)

Research interests

Statistical signal processing and machine learning, with particular interests in matrix factorisation, representation learning, source separation and recommender systems. Statistical estimation, Bayesian inference, optimisation, Markov-chain Monte Carlo, variational approximations, latent variable models, independent component analysis, sparse component analysis, nonnegative matrix factorisation, low-rank approximations, time-frequency representations.


Contact information

Physical address: IRIT-ENSEEIHT, 2 rue Camichel, 31000 Toulouse
Office F419
Email: firstname.lastname(no accents)@irit.fr
Phone: + 33 5 34 32 22 23