136 citations · 211 across the 14 of their papers we have counts for
16 papers
Vision Transformer Finetuning Benefits from Non-Smooth Components
Ambroise Odonnat, Laetitia Chapel, Romain Tavenard +1
The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in t…
Differentiable Generalized Sliced Wasserstein Plans
Laetitia Chapel, Romain Tavenard, Samuel Vaiter
Optimal Transport (OT) has attracted significant interest in the machine learning community, not only for its ability to define meaningful distances between probability distributio…
Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity
Pierre Houedry, Nicolas Courty, Florestan Martin-Baillon +2
Trees and the associated shortest-path tree metrics provide a powerful framework for representing hierarchical and combinatorial structures in data. Given an arbitrary metric space…
Match-And-Deform: Time Series Domain Adaptation through Optimal Transport and Temporal Alignment
François Painblanc, Laetitia Chapel, Nicolas Courty +3
While large volumes of unlabeled data are usually available, associated labels are often scarce. The unsupervised domain adaptation problem aims at exploiting labels from a source…
Fast Optimal Transport through Sliced Wasserstein Generalized Geodesics
Guillaume Mahey, Laetitia Chapel, Gilles Gasso +2
Wasserstein distance (WD) and the associated optimal transport plan have been proven useful in many applications where probability measures are at stake. In this paper, we propose…
Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections
Clément Bonet, Laetitia Chapel, Lucas Drumetz +1
It has been shown beneficial for many types of data which present an underlying hierarchical structure to be embedded in hyperbolic spaces. Consequently, many tools of machine lear…