Direct fixed-weight solver for free-support Wasserstein medians relocates atoms using OT barycentric projections and inverse-distance weights, achieving monotone descent on smoothed objectives with fewer subproblems than nested Weiszfeld baselines.
Miller, Gernot R
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
NeuralBench is a new benchmarking framework for neuroAI models on EEG data that finds foundation models only marginally outperform task-specific ones while many tasks like cognitive decoding stay highly challenging.
Introduces intrinsic barycentric projection via conditional Fréchet means as the optimal deterministic map under squared geodesic loss for OT couplings on Riemannian manifolds, plus a tangential log-exp projection with Euclidean exactness and Monge compatibility.
citing papers explorer
-
NeuralBench: A Unifying Framework to Benchmark NeuroAI Models
NeuralBench is a new benchmarking framework for neuroAI models on EEG data that finds foundation models only marginally outperform task-specific ones while many tasks like cognitive decoding stay highly challenging.