Optimal transport for the multi-model combination of sub-seasonal ensemble forecasts

Autor: Camille Le Coz, Alexis Tantet, Rémi Flamary, Riwal Plougonven

Combining ensemble forecasts from several models has been shown to improve the skill of S2S predictions. One of the most used method for such combination is the “pooled ensemble” method, i.e. the concatenation of the ensemble members from the dif

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1ee8e879ca7c9ae3ad8e13db85527e67
https://doi.org/10.5194/egusphere-egu23-13445

Wasserstein Adversarial Regularization for learning with label noise

Autor: Nicolas Courty, Devis Tuia, Rémi Flamary, Bharath Bhushan Damodaran, Sylvain Lobry, Kilian Fatras

Publikováno v: IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10), 7296-7306
IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (2022) 10
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2021, pp.1-1. ⟨10.1109/TPAMI.2021.3094662⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, pp.1-1. ⟨10.1109/TPAMI.2021.3094662⟩

Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this goal, we p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5054f6217c5c3f76c61145e78829af19
https://doi.org/10.1109/tpami.2021.3094662

Wind power predictions from nowcasts to 4-hour forecasts: a learning approach with variable selection

Autor: Dimitri Bouche, Rémi Flamary, Florence d’Alché-Buc, Riwal Plougonven, Marianne Clausel, Jordi Badosa, Philippe Drobinski

We study the prediction of short term wind speed and wind power (every 10 minutes up to 4 hours ahead). Accurate forecasts for those quantities are crucial to mitigate the negative effects of wind farms' intermittent production on energy systems and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7542968b82ee956156c1350c1c18ac94
http://arxiv.org/abs/2204.09362

Sliding window strategy for convolutional spike sorting with Lasso Algorithm, theoretical guarantees and complexity

Autor: Laurent Dragoni, Rémi Flamary, Karim Lounici, Patricia Reynaud-Bouret

Spike sorting is a class of algorithms used in neuroscience to attribute the time occurences of particular electric signals, called action potential or spike, to neurons. We rephrase this problem as a particular optimization problem : Lasso for convo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a82ac09b55fe6397c77ea712cf7bd4c
https://hal.archives-ouvertes.fr/hal-03410829

An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images

Autor: Rémi Flamary, Bharath Bhushan Damodaran, Nicolas Courty, Vivien Seguy

Publikováno v: Computer Vision and Image Understanding
Computer Vision and Image Understanding, 2020, 191, pp.102863. ⟨10.1016/j.cviu.2019.102863⟩
Computer Vision and Image Understanding, 2020, pp.102863. ⟨10.1016/j.cviu.2019.102863⟩
Computer Vision and Image Understanding, Elsevier, 2020, 191, pp.102863. ⟨10.1016/j.cviu.2019.102863⟩

Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled samples. In

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2ed92162a50c1ef22ab9cc374bde717
https://hal.archives-ouvertes.fr/hal-02174320