The paper establishes regret bounds for mean-field neural network dynamics in continuous-time diffusion settings, yielding constant static regret under displacement convexity and explicit linear regret bounds in the general non-convex case.
This gives a differential inequality for Z Rd Vk(θ)ρ t(dθ), from which we obtain the uniform bound on thek-th moment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Continuous-time Online Learning via Mean-Field Neural Networks: Regret Analysis in Diffusion Environments
The paper establishes regret bounds for mean-field neural network dynamics in continuous-time diffusion settings, yielding constant static regret under displacement convexity and explicit linear regret bounds in the general non-convex case.