196 citations · 700 across the 23 of their papers we have counts for
6 papers · 1 filter
Deterministic Global Optimization over trained Kolmogorov Arnold Networks
Tanuj Karia, Giacomo Lastrucci, Artur M. Schweidtmann
To address the challenge of tractability for optimizing mathematical models in science and engineering, surrogate models are often employed. Recently, a new class of machine learni…
Mixed-Integer Optimisation of Graph Neural Networks for Computer-Aided Molecular Design
Tom McDonald, Calvin Tsay, Artur M. Schweidtmann +1
ReLU neural networks have been modelled as constraints in mixed integer linear programming (MILP), enabling surrogate-based optimisation in various domains and efficient solution o…
Optimization with Trained Machine Learning Models Embedded
Artur M. Schweidtmann, Dominik Bongartz, Alexander Mitsos
Trained ML models are commonly embedded in optimization problems. In many cases, this leads to large-scale NLPs that are difficult to solve to global optimality. While ML models fr…
Obey validity limits of data-driven models
Artur M Schweidtmann, Jana M Weber, Christian Wende +2
Data-driven models are becoming increasingly popular in engineering, on their own or in combination with mechanistic models. Commonly, the trained models are subsequently used in m…
Global Optimization of Gaussian processes
Artur M. Schweidtmann, Dominik Bongartz, Daniel Grothe +4
Gaussian processes~(Kriging) are interpolating data-driven models that are frequently applied in various disciplines. Often, Gaussian processes are trained on datasets and are subs…
Global Deterministic Optimization with Artificial Neural Networks Embedded
Artur M Schweidtmann, Alexander Mitsos
Artificial neural networks (ANNs) are used in various applications for data-driven black-box modeling and subsequent optimization. Herein, we present an efficient method for determ…