5 papers
Bridging Maximum Likelihood and Optimal Transport for Efficient Inference and Model Selection in Stochastic Block Models
Simon Queric, Cédric Vincent-Cuaz, Charles Bouveyron +1
We study inference in stochastic block models (SBMs) through the lens of optimal transport (OT). We first establish that maximum likelihood variational inference (MLVI) can be inte…
GrapHist: Graph Self-Supervised Learning for Histopathology
Sevda ÃÄüt, Cédric Vincent-Cuaz, Natalia Dubljevic +4
Self-supervised vision models have achieved notable success in digital pathology. However, their domain-agnostic transformer architectures are not originally designed to account fo…
Inductive Domain Transfer In Misspecified Simulation-Based Inference
Ortal Senouf, Antoine Wehenkel, Cédric Vincent-Cuaz +2
Simulation-based inference (SBI) is a statistical inference approach for estimating latent parameters of a physical system when the likelihood is intractable but simulations are av…
Revisiting Automatic Data Curation for Vision Foundation Models in Digital Pathology
Boqi Chen, Cédric Vincent-Cuaz, Lydia A. Schoenpflug +12
Vision foundation models (FMs) are accelerating the development of digital pathology algorithms and transforming biomedical research. These models learn, in a self-supervised manne…
Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein
Hugues Van Assel, Cédric Vincent-Cuaz, Nicolas Courty +3
Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR)…