Wasserstein metrics
PulseAugur coverage of Wasserstein metrics — every cluster mentioning Wasserstein metrics across labs, papers, and developer communities, ranked by signal.
-
Wasserstein metrics show improved noise resilience for image similarity
A new paper explores the sensitivity of Wasserstein metrics to noise in image similarity scoring. Researchers derived bounds showing that the error in Wasserstein discrepancy scales with the square root of noise standar…
-
Two new papers explore theoretical underpinnings of score-based generative models
Two new arXiv papers explore score-based generative models from different theoretical angles. The first paper introduces Score Anisotropy Directions (SADs) to analyze network architecture's influence on model biases and…
-
New framework uses Hilbert space for multi-dimensional reinforcement learning
A new research paper introduces KE-DRL, a framework for multi-dimensional distributional reinforcement learning that utilizes Hilbert space mappings. This approach estimates the kernel mean embedding of multi-dimensiona…