Zobrazeno 1 - 10
of 129
pro vyhledávání: '"Flamary, Remi"'
Machine learning applications on signals such as computer vision or biomedical data often face significant challenges due to the variability that exists across hardware devices or session recordings. This variability poses a Domain Adaptation (DA) pr
Externí odkaz:
http://arxiv.org/abs/2407.14303
Autor:
Lalou, Yanis, Gnassounou, Théo, Collas, Antoine, de Mathelin, Antoine, Kachaiev, Oleksii, Odonnat, Ambroise, Gramfort, Alexandre, Moreau, Thomas, Flamary, Rémi
Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. While many methods have been proposed in the literature, fair and rea
Externí odkaz:
http://arxiv.org/abs/2407.11676
Autor:
Krzakala, Paul, Yang, Junjie, Flamary, Rémi, d'Alché-Buc, Florence, Laclau, Charlotte, Labeau, Matthieu
We propose Any2graph, a generic framework for end-to-end Supervised Graph Prediction (SGP) i.e. a deep learning model that predicts an entire graph for any kind of input. The framework is built on a novel Optimal Transport loss, the Partially-Masked
Externí odkaz:
http://arxiv.org/abs/2402.12269
Autor:
Van Assel, Hugues, Vincent-Cuaz, Cédric, Courty, Nicolas, Flamary, Rémi, Frossard, Pascal, Vayer, Titouan
Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR) methods to project data onto lower-dimensional spaces or organizing po
Externí odkaz:
http://arxiv.org/abs/2402.02239
This paper introduces a novel domain adaptation technique for time series data, called Mixing model Stiefel Adaptation (MSA), specifically addressing the challenge of limited labeled signals in the target dataset. Leveraging a domain-dependent mixing
Externí odkaz:
http://arxiv.org/abs/2402.03345
Ensemble forecasts and their combination are explored from the perspective of a probability space. Manipulating ensemble forecasts as discrete probability distributions, multi-model ensembles (MMEs) are reformulated as barycenters of these distributi
Externí odkaz:
http://arxiv.org/abs/2310.17933
We present a versatile adaptation of existing dimensionality reduction (DR) objectives, enabling the simultaneous reduction of both sample and feature sizes. Correspondances between input and embedding samples are computed through a semi-relaxed Grom
Externí odkaz:
http://arxiv.org/abs/2310.03398
Regularising the primal formulation of optimal transport (OT) with a strictly convex term leads to enhanced numerical complexity and a denser transport plan. Many formulations impose a global constraint on the transport plan, for instance by relying
Externí odkaz:
http://arxiv.org/abs/2310.02925
Publikováno v:
Mathematics of Computation (2024)
The Sliced Wasserstein (SW) distance has become a popular alternative to the Wasserstein distance for comparing probability measures. Widespread applications include image processing, domain adaptation and generative modelling, where it is common to
Externí odkaz:
http://arxiv.org/abs/2307.10352
In many machine learning applications on signals and biomedical data, especially electroencephalogram (EEG), one major challenge is the variability of the data across subjects, sessions, and hardware devices. In this work, we propose a new method cal
Externí odkaz:
http://arxiv.org/abs/2305.18831