A novel consensus-based optimization algorithm with α-stable jumps is formulated at the particle level, yielding a fractional Fokker-Planck equation, a rigorous convergence proof, and improved numerical performance over diffusion-based methods.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Consensus-based optimization with $\alpha$-stable jump processes
A novel consensus-based optimization algorithm with α-stable jumps is formulated at the particle level, yielding a fractional Fokker-Planck equation, a rigorous convergence proof, and improved numerical performance over diffusion-based methods.
-
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.