collaborators

6 papers

cs.LG2026

ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening

Antoine de Mathelin, Christopher Tosh, Wesley Tansey

Treating patients with combinations of drugs reduces the risk of resistance to any individual drug. Finding effective combinations is difficult because the large search space makes…

stat.ME2026

Empirically Calibrated Conditional Independence Tests

Milleno Pan, Antoine de Mathelin, Wesley Tansey

Conditional independence tests (CIT) are widely used for causal discovery and feature selection. Even with false discovery rate (FDR) control procedures, they often fail to provide…

cs.LG2025

SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities

Yanis Lalou, Théo Gnassounou, Antoine Collas +6

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.…

cs.LG2025

Addressing the Cold-Start Problem for Personalized Combination Drug Screening

Antoine de Mathelin, Christopher Tosh, Wesley Tansey

Personalizing combination therapies in oncology requires navigating an immense space of possible drug and dose combinations, a task that remains largely infeasible through exhausti…

cs.LG2025

OneBatchPAM: A Fast and Frugal K-Medoids Algorithm

Antoine de Mathelin, Nicolas Enrique Cecchi, François Deheeger +2

This paper proposes a novel k-medoids approximation algorithm to handle large-scale datasets with reasonable computational time and memory complexity. We develop a local-search alg…

cs.LG2025

Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization

Antoine de Mathelin, François Deheeger, Mathilde Mougeot +1

This paper deals with uncertainty quantification and out-of-distribution detection in deep learning using Bayesian and ensemble methods. It proposes a practical solution to the lac…