Establishes functional LLN and LDP for multi-scale McKean-Vlasov diffusions with super-linear kernels via lifted semigroup arguments and generalized viable pairs.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
ProxiCBO is a new interacting-particle method that merges CBO with proximal gradients, establishes global convergence for finite-particle continuous dynamics, and outperforms baselines on one-bit signal recovery and single-photon lidar parameter estimation.
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
-
Asymptotics of Multi-Scale McKean--Vlasov Diffusions with Super-Linear Kernels: a Lifted Semigroup Approach
Establishes functional LLN and LDP for multi-scale McKean-Vlasov diffusions with super-linear kernels via lifted semigroup arguments and generalized viable pairs.
-
ProxiCBO: A Provably Convergent Consensus-Based Method for Composite Optimization
ProxiCBO is a new interacting-particle method that merges CBO with proximal gradients, establishes global convergence for finite-particle continuous dynamics, and outperforms baselines on one-bit signal recovery and single-photon lidar parameter estimation.
-
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.
- Uniform-in-time propagation of chaos for Second-Order Consensus-Based Optimization