activity
20222025
most citedOptimizing Objective Functions from Trained ReLU Neural Networks via Sampling

2 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

math.OC2022★ 2 cited

Optimizing Objective Functions from Trained ReLU Neural Networks via Sampling

Georgia Perakis, Asterios Tsiourvas

This paper introduces scalable, sampling-based algorithms that optimize trained neural networks with ReLU activations. We first propose an iterative algorithm that takes advantage…

math.NA2022

Discrete Gradient Flow Approximations of High Dimensional Evolution Partial Differential Equations via Deep Neural Networks

Emmanuil H. Georgoulis, Michail Loulakis, Asterios Tsiourvas

We consider the approximation of initial/boundary value problems involving, possibly high-dimensional, dissipative evolution partial differential equations (PDEs) using a deep neur…