Lifts CCCP to Wasserstein space for DC functionals on measures, proves almost stationarity under smoothness/strong-convexity assumptions, and applies to MMD/ED with local convergence and faster empirical runs.
A subdifferential characteri- zation via Busemann functions and applications to DC optimization on Hadamard manifolds
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A robust Riemannian Levenberg-Marquardt algorithm is formulated in block-wise form, with convergence results carried over from prior work and demonstrated via an open-source Manopt.jl implementation on tasks including geodesic regression and Procrustes analysis.
citing papers explorer
-
Difference of Convex Programming in the Wasserstein Space with Applications to MMD Optimization
Lifts CCCP to Wasserstein space for DC functionals on measures, proves almost stationarity under smoothness/strong-convexity assumptions, and applies to MMD/ED with local convergence and faster empirical runs.