Decorrelation using optimal transport.

Being able to decorrelate a feature space from protected attributes is an area of active research and study in ethics, fairness, and also natural sciences. We introduce a novel decorrelation method using Convex Neural Optimal Transport Solvers (Cnots) that is able to decorrelate a continuous feature space against protected attributes with optimal transport. We demonstrate how well it performs in the context of jet classification in high energy physics, where classifier scores are desired to be decorrelated from the mass of a jet.

Pharmacists' considerations on non-medical switching at the hospital: a systematic review of the economic outcomes of cost-saving therapeutic drug classes.

Objectives: Non-medical switching (NMS) strategies have the capacity to reduce overall costs in hospitals while maintaining a high level of care. However, the most appropriate diseases and/or medicines for NMS strategies are still vague. The aim of this review was to give a state-of-the-art summary regarding the economic outcomes resulting from the use of NMS strategies and to discuss whether they would be implementable in a hospital inpatient setting.

Exopolymeric Substances Control Microbial Community Structure and Function by Contributing to both C and Fe Nutrition in Fe-Limited Southern Ocean Provinces.

Organic ligands such as exopolymeric substances (EPS) are known to form complexes with iron (Fe) and modulate phytoplankton growth. However, the effect of organic ligands on bacterial and viral communities remains largely unknown. Here, we assessed how Fe associated with organic ligands influences phytoplankton, microbial, and viral abundances and their diversity in the Southern Ocean.