no code implementations • 13 Feb 2024 • Jose Pablo Folch, Calvin Tsay, Robert M Lee, Behrang Shafei, Weronika Ormaniec, Andreas Krause, Mark van der Wilk, Ruth Misener, Mojmír Mutný
Bayesian optimization is a methodology to optimize black-box functions.
no code implementations • 29 Jan 2024 • Joel A. Paulson, Calvin Tsay
Bayesian optimization (BO) is a powerful technology for optimizing noisy expensive-to-evaluate black-box functions, with a broad range of real-world applications in science, engineering, economics, manufacturing, and beyond.
no code implementations • 2 Dec 2023 • Tom McDonald, Calvin Tsay, Artur M. Schweidtmann, Neil Yorke-Smith
ReLU neural networks have been modelled as constraints in mixed integer linear programming (MILP), enabling surrogate-based optimisation in various domains and efficient solution of machine learning certification problems.
no code implementations • 1 Dec 2023 • Jose Pablo Folch, James Odgers, Shiqiang Zhang, Robert M Lee, Behrang Shafei, David Walz, Calvin Tsay, Mark van der Wilk, Ruth Misener
There has been a surge in interest in data-driven experimental design with applications to chemical engineering and drug manufacturing.
no code implementations • 29 Apr 2023 • Joey Huchette, Gonzalo Muñoz, Thiago Serra, Calvin Tsay
In the past decade, deep learning became the prevalent methodology for predictive modeling thanks to the remarkable accuracy of deep neural networks in tasks such as computer vision and natural language processing.
no code implementations • 20 Feb 2023 • Shudian Zhao, Calvin Tsay, Jan Kronqvist
In this work, we develop a novel input feature selection framework for ReLU-based deep neural networks (DNNs), which builds upon a mixed-integer optimization approach.
1 code implementation • 3 Feb 2023 • Jaime Sabal Bermúdez, Antonio del Rio Chanona, Calvin Tsay
We introduce Distributional Constrained Policy Optimization (DCPO), a novel approach for reliable constraint satisfaction in RL.
Distributional Reinforcement Learning Policy Gradient Methods +2
1 code implementation • 11 Nov 2022 • Jose Pablo Folch, Robert M Lee, Behrang Shafei, David Walz, Calvin Tsay, Mark van der Wilk, Ruth Misener
Bayesian Optimization is a useful tool for experiment design.
1 code implementation • 2 Jul 2022 • Alexander Thebelt, Calvin Tsay, Robert M. Lee, Nathan Sudermann-Merx, David Walz, Behrang Shafei, Ruth Misener
Tree ensembles can be well-suited for black-box optimization tasks such as algorithm tuning and neural architecture search, as they achieve good predictive performance with little or no manual tuning, naturally handle discrete feature spaces, and are relatively insensitive to outliers in the training data.
no code implementations • 10 Feb 2022 • Jan Kronqvist, Ruth Misener, Calvin Tsay
We develop a class of mixed-integer formulations for disjunctive constraints intermediate to the big-M and convex hull formulations in terms of relaxation strength.
1 code implementation • 4 Feb 2022 • Francesco Ceccon, Jordan Jalving, Joshua Haddad, Alexander Thebelt, Calvin Tsay, Carl D. Laird, Ruth Misener
The optimization and machine learning toolkit (OMLT) is an open-source software package incorporating neural network and gradient-boosted tree surrogate models, which have been trained using machine learning, into larger optimization problems.
2 code implementations • 31 Jan 2022 • Jose Pablo Folch, Shiqiang Zhang, Robert M Lee, Behrang Shafei, David Walz, Calvin Tsay, Mark van der Wilk, Ruth Misener
Bayesian Optimization is a very effective tool for optimizing expensive black-box functions.
no code implementations • 25 Jan 2022 • Alexander Thebelt, Johannes Wiebe, Jan Kronqvist, Calvin Tsay, Ruth Misener
For each of these four data characteristics, we discuss applications where these data characteristics arise and show how current chemical engineering research is extending the fields of data science and machine learning to incorporate these challenges.
1 code implementation • 4 Nov 2021 • Alexander Thebelt, Calvin Tsay, Robert M. Lee, Nathan Sudermann-Merx, David Walz, Tom Tranter, Ruth Misener
Energy systems optimization problems are complex due to strongly non-linear system behavior and multiple competing objectives, e. g. economic gain vs. environmental impact.
1 code implementation • NeurIPS 2021 • Calvin Tsay, Jan Kronqvist, Alexander Thebelt, Ruth Misener
This paper introduces a class of mixed-integer formulations for trained ReLU neural networks.
no code implementations • 29 Jan 2021 • Jan Kronqvist, Ruth Misener, Calvin Tsay
This work develops a class of relaxations in between the big-M and convex hull formulations of disjunctions, drawing advantages from both.