Tyler H. Chang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tyler H. Chang has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
Layne T. Watson
Virginia Polytechnic Institute and State University, Blacksburg, Va
8 shared publicationsThomas C. H. Lux
Virginia Polytechnic Institute and State University, Blacksburg, Va
8 shared publicationsKirk W. Cameron
Virginia Polytechnic Institute and State University, Blacksburg, Va
5 shared publications- Layne T. Watson
Virginia Polytechnic Institute and State University
5 shared publications - Thomas Lux
Meta, Menlo Park, CA, USA
5 shared publications Yili Hong
Virginia Polytechnic Institute and State University, Blacksburg, Va
5 shared publications
Latest Publications
- 1 January 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
- Vol. 38 (1) , 269-294
Designing a Framework for Solving Multiobjective Simulation Optimization Problems
Multiobjective simulation optimization (MOSO) problems are optimization problems with multiple conflicting objectives, where evaluation of at least one of the objectives depends on a black-box numerical code or real-world experiment, which we refer to as a simulation. Whereas an extensive body of research is dedicated to developing new algorithms and methods for solving these and related problems, it is challenging and time-consuming to integrate these techniques into real-world production-ready solvers. This is partly because of the diversity and complexity of modern state-of-the-art MOSO algorithms and methods and partly because of the complexity and specificity of many real-world problems and their corresponding computing environments. The complexity of this problem is only compounded when introducing potentially complex and/or domain-specific surrogate-modeling techniques, problem formulations, design spaces, and data acquisition functions. This paper carefully surveys the current state of the art in MOSO algorithms, techniques, and solvers, as well as problem types and computational environments where MOSO is commonly applied. We then present several key challenges in the design of a parallel multiobjective simulation optimization framework (ParMOO) and how they have been addressed. Finally, we provide two case studies demonstrating how customized ParMOO solvers can be quickly built and deployed to solve real-world MOSO problems. History: Accepted by Ted Ralphs, Area Editor for Software Tools. Funding: This work was supported by US DOE, Office of Science, Advanced Scientific Computing Research, SciDAC Program [Grants DE-AC02-05CH11231 and DE-AC02-06CH11357]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0250 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0250 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
- 1 January 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
- Vol. 38 (1) , 269-294
Designing a Framework for Solving Multiobjective Simulation Optimization Problems
Multiobjective simulation optimization (MOSO) problems are optimization problems with multiple conflicting objectives, where evaluation of at least one of the objectives depends on a black-box numerical code or real-world experiment, which we refer to as a simulation. Whereas an extensive body of research is dedicated to developing new algorithms and methods for solving these and related problems, it is challenging and time-consuming to integrate these techniques into real-world production-ready solvers. This is partly because of the diversity and complexity of modern state-of-the-art MOSO algorithms and methods and partly because of the complexity and specificity of many real-world problems and their corresponding computing environments. The complexity of this problem is only compounded when introducing potentially complex and/or domain-specific surrogate-modeling techniques, problem formulations, design spaces, and data acquisition functions. This paper carefully surveys the current state of the art in MOSO algorithms, techniques, and solvers, as well as problem types and computational environments where MOSO is commonly applied. We then present several key challenges in the design of a parallel multiobjective simulation optimization framework (ParMOO) and how they have been addressed. Finally, we provide two case studies demonstrating how customized ParMOO solvers can be quickly built and deployed to solve real-world MOSO problems. History: Accepted by Ted Ralphs, Area Editor for Software Tools. Funding: This work was supported by US DOE, Office of Science, Advanced Scientific Computing Research, SciDAC Program [Grants DE-AC02-05CH11231 and DE-AC02-06CH11357]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0250 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0250 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
- 4 March 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for ParMOO Solvers: Sample Simulation Optimization Problems and Solvers
This repository contains several multiobjective simulation optimization (MOSO) problem definitions, scripts for solving those problems with an archived version (v0.2.2) of the ParMOO software, and an archived version of the ParMOO software. The data collected in this repository were used in the research reported on in the paper Designing a Framework for Solving Multiobjective Simulation Optimization Problems by Tyler H. Chang and Stefan M. Wild.
- 4 March 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for ParMOO Solvers: Sample Simulation Optimization Problems and Solvers
This repository contains several multiobjective simulation optimization (MOSO) problem definitions, scripts for solving those problems with an archived version (v0.2.2) of the ParMOO software, and an archived version of the ParMOO software. The data collected in this repository were used in the research reported on in the paper Designing a Framework for Solving Multiobjective Simulation Optimization Problems by Tyler H. Chang and Stefan M. Wild.
- 9 January 2025
- Published by Elsevier in Journal of Computational Physics
- Vol. 524
Leveraging interpolation models and error bounds for verifiable scientific machine learning
- 9 January 2025
- Published by Elsevier in Journal of Computational Physics
- Vol. 524
Leveraging interpolation models and error bounds for verifiable scientific machine learning
- Open Access
- 28 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
- Vol. 50 (2) , 1-8
Remark on Algorithm 1012: Computing Projections with Large Datasets
In ACM TOMS Algorithm 1012, the DELAUNAYSPARSE software is given for performing Delaunay interpolation in medium to high dimensions. When extrapolating outside the convex hull of the training set, DELAUNAYSPARSE calls the nonnegative least squares solver DWNNLS to compute projections onto the convex hull. However, DWNNLS and many other available sum-of-squares optimization solvers were not intended for usage with many variable problems, which result from the large training sets that are typical in machine learning applications. Thus, a new PROJECT subroutine is given, based on the highly customizable quadratic program solver BQPD . This solution is shown to be as robust as DELAUNAYSPARSE for projection onto both synthetic and real-world datasets, where other available solvers frequently fail. Although it is intended as an update for DELAUNAYSPARSE , due to the difficulty and prevalence of the problem, this solution is likely to be of external interest as well.
- 28 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
- Vol. 50 (2) , 1-8
Open AccessRemark on Algorithm 1012: Computing Projections with Large Datasets
In ACM TOMS Algorithm 1012, the DELAUNAYSPARSE software is given for performing Delaunay interpolation in medium to high dimensions. When extrapolating outside the convex hull of the training set, DELAUNAYSPARSE calls the nonnegative least squares solver DWNNLS to compute projections onto the convex hull. However, DWNNLS and many other available sum-of-squares optimization solvers were not intended for usage with many variable problems, which result from the large training sets that are typical in machine learning applications. Thus, a new PROJECT subroutine is given, based on the highly customizable quadratic program solver BQPD . This solution is shown to be as robust as DELAUNAYSPARSE for projection onto both synthetic and real-world datasets, where other available solvers frequently fail. Although it is intended as an update for DELAUNAYSPARSE , due to the difficulty and prevalence of the problem, this solution is likely to be of external interest as well.
- Open Access
A framework for fully autonomous design of materials via multiobjective optimization and active learning: challenges and next steps
In order to deploy machine learning in a real-world self-driving laboratory where data acquisition is costly and there are multiple competing design criteria, systems need to be able to intelligently sample while balancing performance trade-offs and constraints. For these reasons, we present an active learning process based on multiobjective black-box optimization with continuously updated machine learning models. This workflow is built on open-source technologies for real-time data streaming and modular multiobjective optimization software development. We demonstrate a proof of concept for this workflow through the autonomous operation of a continuous-flow chemistry laboratory, which identifies ideal manufacturing conditions for the electrolyte 2,2,2-trifluoroethyl methyl carbonate.
Open AccessA framework for fully autonomous design of materials via multiobjective optimization and active learning: challenges and next steps
In order to deploy machine learning in a real-world self-driving laboratory where data acquisition is costly and there are multiple competing design criteria, systems need to be able to intelligently sample while balancing performance trade-offs and constraints. For these reasons, we present an active learning process based on multiobjective black-box optimization with continuously updated machine learning models. This workflow is built on open-source technologies for real-time data streaming and modular multiobjective optimization software development. We demonstrate a proof of concept for this workflow through the autonomous operation of a continuous-flow chemistry laboratory, which identifies ideal manufacturing conditions for the electrolyte 2,2,2-trifluoroethyl methyl carbonate.
- Open Access
- 21 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
- Vol. 49 (1) , 1-17
Algorithm 1031: MQSI—Monotone Quintic Spline Interpolation
MQSI is a Fortran 2003 subroutine for constructing monotone quintic spline interpolants to univariate monotone data. Using sharp theoretical monotonicity constraints, first and second derivative estimates at data provided by a quadratic facet model are refined to produce a univariate C 2 monotone interpolant. Algorithm and implementation details, complexity and sensitivity analyses, usage information, a brief performance study, and comparisons with other spline approaches are included.
- 21 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
- Vol. 49 (1) , 1-17
Open AccessAlgorithm 1031: MQSI—Monotone Quintic Spline Interpolation
MQSI is a Fortran 2003 subroutine for constructing monotone quintic spline interpolants to univariate monotone data. Using sharp theoretical monotonicity constraints, first and second derivative estimates at data provided by a quadratic facet model are refined to produce a univariate C 2 monotone interpolant. Algorithm and implementation details, complexity and sensitivity analyses, usage information, a brief performance study, and comparisons with other spline approaches are included.
- Open Access
- 3 February 2023
- Published by The Open Journal in Journal of Open Source Software
- Vol. 8 (82) , 4468
ParMOO: A Python library for parallel multiobjective simulation optimization
A multiobjective optimization problem (MOOP) is an optimization problem in which multiple objectives are optimized simultaneously. The goal of a MOOP is to find solutions that describe the tradeoff between these (potentially conflicting) objectives. Such a tradeoff surface is called the Pareto front. Real-world MOOPs may also involve constraints-additional hard rules that every solution must adhere to. In a multiobjective simulation optimization problem, the objectives are derived from the outputs of one or more computationally expensive simulations. Such problems are ubiquitous in science and engineering.
- 3 February 2023
- Published by The Open Journal in Journal of Open Source Software
- Vol. 8 (82) , 4468
Open AccessParMOO: A Python library for parallel multiobjective simulation optimization
A multiobjective optimization problem (MOOP) is an optimization problem in which multiple objectives are optimized simultaneously. The goal of a MOOP is to find solutions that describe the tradeoff between these (potentially conflicting) objectives. Such a tradeoff surface is called the Pareto front. Real-world MOOPs may also involve constraints-additional hard rules that every solution must adhere to. In a multiobjective simulation optimization problem, the objectives are derived from the outputs of one or more computationally expensive simulations. Such problems are ubiquitous in science and engineering.
- Open Access
Comparison of Multiobjective Optimization Methods for the LCLS-II Photoinjector
Particle accelerators are among some of the largest science experiments in the world and can consist of thousands of components with a wide variety of input ranges. These systems can easily become unwieldy optimization problems during design and operations studies. Starting in the early 2000s, searching for better beam dynamics configurations became synonymous with heuristic optimization methods in the accelerator physics community. Genetic algorithms and particle swarm optimization are currently the most widely used. These algorithms can take thousands of simulation evaluations to find optimal solutions for one machine prototype. For large facilities such as the Linac Coherent Light Source (LCLS) and others, this equates to a limited exploration of many possible design configurations. In this paper, the LCLS-II photoinjector is optimized with three optimization algorithms. All optimizations were started from both a uniform random and Latin hypercube sample. In all cases, the optimizations started from Latin hypercube samples outperformed optimizations started from uniform samples. All three algorithms were able to optimize the photoinjector, with the model-based methods approximating the Pareto front in fewer simulation evaluations. This work, in combination with previous optimization observations, indicates objective penalties have a strong impact on the efficiency of such methods. In general, we recommend heuristic methods for initial optimizations and model-based methods when information about the objective space is available.
Open AccessComparison of Multiobjective Optimization Methods for the LCLS-II Photoinjector
Particle accelerators are among some of the largest science experiments in the world and can consist of thousands of components with a wide variety of input ranges. These systems can easily become unwieldy optimization problems during design and operations studies. Starting in the early 2000s, searching for better beam dynamics configurations became synonymous with heuristic optimization methods in the accelerator physics community. Genetic algorithms and particle swarm optimization are currently the most widely used. These algorithms can take thousands of simulation evaluations to find optimal solutions for one machine prototype. For large facilities such as the Linac Coherent Light Source (LCLS) and others, this equates to a limited exploration of many possible design configurations. In this paper, the LCLS-II photoinjector is optimized with three optimization algorithms. All optimizations were started from both a uniform random and Latin hypercube sample. In all cases, the optimizations started from Latin hypercube samples outperformed optimizations started from uniform samples. All three algorithms were able to optimize the photoinjector, with the model-based methods approximating the Pareto front in fewer simulation evaluations. This work, in combination with previous optimization observations, indicates objective penalties have a strong impact on the efficiency of such methods. In general, we recommend heuristic methods for initial optimizations and model-based methods when information about the objective space is available.
- Open Access
- 10 September 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
- Vol. 48 (3) , 1-34
Algorithm 1028: VTMOP: Solver for Blackbox Multiobjective Optimization Problems
VTMOP is a Fortran 2008 software package containing two Fortran modules for solving computationally expensive bound-constrained blackbox multiobjective optimization problems. VTMOP implements the algorithm of [ 32 ], which handles two or more objectives, does not require any derivatives, and produces well-distributed points over the Pareto front. The first module contains a general framework for solving multiobjective optimization problems by combining response surface methodology, trust region methodology, and an adaptive weighting scheme. The second module features a driver subroutine that implements this framework when the objective functions can be wrapped as a Fortran subroutine. Support is provided for both serial and parallel execution paradigms, and VTMOP is demonstrated on several test problems as well as one real-world problem in the area of particle accelerator optimization.
- 10 September 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
- Vol. 48 (3) , 1-34
Open AccessAlgorithm 1028: VTMOP: Solver for Blackbox Multiobjective Optimization Problems
VTMOP is a Fortran 2008 software package containing two Fortran modules for solving computationally expensive bound-constrained blackbox multiobjective optimization problems. VTMOP implements the algorithm of [ 32 ], which handles two or more objectives, does not require any derivatives, and produces well-distributed points over the Pareto front. The first module contains a general framework for solving multiobjective optimization problems by combining response surface methodology, trust region methodology, and an adaptive weighting scheme. The second module features a driver subroutine that implements this framework when the objective functions can be wrapped as a Fortran subroutine. Support is provided for both serial and parallel execution paradigms, and VTMOP is demonstrated on several test problems as well as one real-world problem in the area of particle accelerator optimization.
- Open Access
- 17 February 2022
- Published by Taylor & Francis in Journal of Quality Technology
- Vol. 55 (1) , 88-103
Design strategies and approximation methods for high-performance computing variability management
Performance variability management is an active research area in high-performance computing (HPC). In this article, we focus on input/output (I/O) variability, which is a complicated function that is affected by many system factors. To study the performance variability, computer scientists often use grid-based designs (GBDs) which are equivalent to full factorial designs to collect I/O variability data, and use mathematical approximation methods to build a prediction model. Mathematical approximation models, as deterministic methods, could be biased particularly if extrapolations are needed. In statistics literature, space-filling designs (SFDs) and surrogate models such as Gaussian process (GP) are popular for data collection and building predictive models. The applicability of SFDs and surrogates in the HPC variability management setting, however, needs investigation. In this case study, we investigate their applicability in the HPC setting in terms of design efficiency, prediction accuracy, and scalability. We first customize the existing SFDs so that they can be applied in the HPC setting. We conduct a comprehensive investigation of design strategies and the prediction ability of approximation methods. We use both synthetic data simulated from three test functions and the real data from the HPC setting. We then compare different methods in terms of design efficiency, prediction accuracy, and scalability. In our synthetic and real data analysis, GP with SFDs outperforms in most scenarios. With respect to the choice of approximation models, GP is recommended if the data are collected by SFDs. If data are collected using GBDs, both GP and Delaunay can be considered. With the best choice of approximation method, the performance of SFDs and GBD depends on the property of the underlying surface. For the cases in which SFDs perform better, the number of design points needed for SFDs is about half of or less than that of the GBD to achieve the same prediction accuracy. Although we observe that the GBD can also outperform SFDs for smooth underlying surface, GBD is not scalable to high dimensional experimental regions. Therefore, SFDs that can be tailored to high dimension and non-smooth surface are recommended especially when large numbers of input factors need to be considered in the model. This article has online supplementary materials.
- 17 February 2022
- Published by Taylor & Francis in Journal of Quality Technology
- Vol. 55 (1) , 88-103
Open AccessDesign strategies and approximation methods for high-performance computing variability management
Performance variability management is an active research area in high-performance computing (HPC). In this article, we focus on input/output (I/O) variability, which is a complicated function that is affected by many system factors. To study the performance variability, computer scientists often use grid-based designs (GBDs) which are equivalent to full factorial designs to collect I/O variability data, and use mathematical approximation methods to build a prediction model. Mathematical approximation models, as deterministic methods, could be biased particularly if extrapolations are needed. In statistics literature, space-filling designs (SFDs) and surrogate models such as Gaussian process (GP) are popular for data collection and building predictive models. The applicability of SFDs and surrogates in the HPC variability management setting, however, needs investigation. In this case study, we investigate their applicability in the HPC setting in terms of design efficiency, prediction accuracy, and scalability. We first customize the existing SFDs so that they can be applied in the HPC setting. We conduct a comprehensive investigation of design strategies and the prediction ability of approximation methods. We use both synthetic data simulated from three test functions and the real data from the HPC setting. We then compare different methods in terms of design efficiency, prediction accuracy, and scalability. In our synthetic and real data analysis, GP with SFDs outperforms in most scenarios. With respect to the choice of approximation models, GP is recommended if the data are collected by SFDs. If data are collected using GBDs, both GP and Delaunay can be considered. With the best choice of approximation method, the performance of SFDs and GBD depends on the property of the underlying surface. For the cases in which SFDs perform better, the number of design points needed for SFDs is about half of or less than that of the GBD to achieve the same prediction accuracy. Although we observe that the GBD can also outperform SFDs for smooth underlying surface, GBD is not scalable to high dimensional experimental regions. Therefore, SFDs that can be tailored to high dimension and non-smooth surface are recommended especially when large numbers of input factors need to be considered in the model. This article has online supplementary materials.