Learning Prescriptive ReLU Networks

no code implementations • 1 Jun 2023 • Wei Sun, Asterios Tsiourvas

We study the problem of learning optimal policy from a set of discrete treatment options using observational data.

Optimizing Objective Functions from Trained ReLU Neural Networks via Sampling

no code implementations • 27 May 2022 • Georgia Perakis, Asterios Tsiourvas

We first propose an iterative algorithm that takes advantage of the piecewise linear structure of ReLU neural networks and reduces the initial mixed-integer optimization problem (MIP) into multiple easy-to-solve linear optimization problems (LPs) through sampling.