A unified diffusion-based particle framework for stochastic optimisation with intractable gradients, with exponential contraction and finite-particle error bounds, instantiated as new momentum and higher-order Langevin algorithms.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Particle-based Generalised Stochastic Optimisation
A unified diffusion-based particle framework for stochastic optimisation with intractable gradients, with exponential contraction and finite-particle error bounds, instantiated as new momentum and higher-order Langevin algorithms.