The paper proposes the ANJD flow and AVNSG operator to generate càdlàg trajectories via sequential MMD-gradient descent in Marcus-signature RKHS with generalisation bounds.
Neural stochastic differential equations: deep latent Gaussian models in the diffusion limit
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
ARL lifts states into signature-augmented manifolds and employs self-consistent proxies of future path-laws to enable deterministic expected-return evaluation while preserving contraction mappings in jump-diffusion environments.
Weak-form spatial averaging plus a drift-informed correction recovers symbolic drift and diffusion of SDEs from trajectories to within about 5% on three benchmarks.
citing papers explorer
-
Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS
The paper proposes the ANJD flow and AVNSG operator to generate càdlàg trajectories via sequential MMD-gradient descent in Marcus-signature RKHS with generalisation bounds.
-
Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions
ARL lifts states into signature-augmented manifolds and employs self-consistent proxies of future path-laws to enable deterministic expected-return evaluation while preserving contraction mappings in jump-diffusion environments.
-
Data-Driven Weak-form Discovery of Stochastic Systems
Weak-form spatial averaging plus a drift-informed correction recovers symbolic drift and diffusion of SDEs from trajectories to within about 5% on three benchmarks.