Gaussian particles in a linearized Bures-Wasserstein space perform consensus optimization for variational inference and outperform deterministic gradient methods on low-dimensional non-log-concave targets.
Linearized opti- mal transport for collider events
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The shadow projection onto couplings is bi-Hölder continuous in Wasserstein distance, yielding explicit sample complexity rates for its estimation.
citing papers explorer
-
Variational inference via Gaussian interacting particles in the Bures-Wasserstein geometry
Gaussian particles in a linearized Bures-Wasserstein space perform consensus optimization for variational inference and outperform deterministic gradient methods on low-dimensional non-log-concave targets.
-
Quantitative Stability of the Shadow for Wasserstein Projections and Sample Complexity
The shadow projection onto couplings is bi-Hölder continuous in Wasserstein distance, yielding explicit sample complexity rates for its estimation.