Statistical Learning
Markovian Sliced Wasserstein Distances: Beyond Independent Projections
Sliced Wasserstein (SW) distance suffers from redundant projections due to independent uniform random projecting directions.
A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods Veit D. Wild
We establish the first mathematically rigorous link between Bayesian, variational Bayesian, and ensemble methods. A key step towards this is to reformulate the non-convex optimisation problem typically encountered in deep learning as a convex optimisation in the space of probability measures.
Federated Multi-Objective Learning
Pareto stationary solution that is not improvable for all objectives without sacrificing some objectives.
