The paper shows that a simple L2 weight constraint suffices to enforce the regularity conditions needed for the existing risk bound, and demonstrates the approach on a simulated 2D diffusion.
and Koike, Y.: Drift estimation for a multi-dimensional diffusion process using deep neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
math.ST 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Neural Drift Estimation for Ergodic Diffusions: Non-parametric Analysis and Numerical Exploration
The paper shows that a simple L2 weight constraint suffices to enforce the regularity conditions needed for the existing risk bound, and demonstrates the approach on a simulated 2D diffusion.