Research

Multiple mathematical models are often available for engineering processes, differing in scale (e.g., models of materials vs the processes they are used in) or in rigor (e.g., models for process design vs for control). We investigate methods to link inherently related models for optimal decision making, often by embedding reduced-order “surrogate” models in larger optimisation problems.

Broadly speaking, we are a systems engineering group, and we study frameworks for sequential decision making under uncertainty. We combine fundamental research in optimisation (particularly mixed-integer programming) and machine learning (particularly statistical learning) with systematic frameworks linking these fundamentals to solve engineering challenges.

Ongoing themes include (1) optimisation methods for machine learning models, (2) deriving new (statistical) reduced-order models, and (3) applications in process and energy systems. Finally, these research strands coincide with (4) generic advancements in optimisation and software. Please see further details below (single page for mobile platforms):


1. Optimisation of Trained Machine Learning Models

Many applications embed trained machine learning (ML) models in optimisation problems. For example, ML models can be used as surrogates for functions that are otherwise difficult to represent, such as acquisition functions for black-box optimisation. On the other hand, optimisation can be used to investigate extreme behaviour (e.g., adversarial inputs) of a trained model. Our research here studies optimisation formulations for trained ML models, with a goal of improving performance and scalability.

Representative publications:

  • Xie, Y., Zhang, S., Paulson, J., & Tsay, C. (2025). Global optimization of Gaussian process acquisition functions using a piecewise-linear kernel approximation. AISTATS 2025 link
  • Thebelt, A., Tsay, C., Lee, R. M., Sudermann-Merx, N., Walz, D., Shafei, B., & Misener, R. (2022). Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spaces. NeurIPS arXiv
  • Tsay, C., Kronqvist, J., Thebelt, A., & Misener, R. (2021). Partition-based formulations for mixed-integer optimization of trained ReLU neural networks. NeurIPS link arXiv
  • Tsay, C. (2021). Sobolev trained neural network surrogate models for optimization. Comput. Chem. Eng. link preprint


Some review and survey papers

Current Opinion in Green & Sustainable Chemistry 2025

Bayesian optimization & process systems
(2025)

Chemical Engineering Science 2022

Chemical engineering & machine learning
(2022)

Annual Review of Chemical and Biomolecular Engineering 2020

Process control & energy efficiency
(2020)

Industrial & Engineering Chemistry Research 2019

Bridging time & length scales
(2019)