About this document
Neural Approximation for Probabilistic Constraints by Shu-Bo Yang is a document available to read on EtoBox.
This document introduces a neural network approach for solving probabilistic constrained programs (PCPs). It reformulates probabilistic constraints as quantile functions, then uses a sample-based neural network to approximate the quantile function. The statistical guarantees of the neural approximation are analyzed by showing convergence and feasibility. A simulated annealing algorithm is revised to solve PCPs using the neural approximation. The method is validated on an interval predictor model of wind pow
- Author
- Shu-Bo Yang
- Language
- EN