A carefully regularized neural network trained on the BAR residual recovers Laplace transforms of high-dimensional RBM stationary distributions well enough for near-exact tail-probability inversion up to 30 dimensions.
Dynamic control of stochastic matching systems in heavy traffic: An effective computational method for high-dimensional problems.arXiv preprint arXiv:2509.00809, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Learning Method for Stationary Distribution of Reflected Brownian Motion
A carefully regularized neural network trained on the BAR residual recovers Laplace transforms of high-dimensional RBM stationary distributions well enough for near-exact tail-probability inversion up to 30 dimensions.