About Me
I specialize in artificial intelligence (AI) / machine learning (ML) research and engineering. I write and deploy high performance code, and also develop mathematical theory. My unique ML skills are around distribution outcome prediction, interpretable models, black box optimization, convex optimization, and models that work well with small amounts of data.
Publications
Alternate listings at Google Scholar, DBLP (imperfect matches), and ORCID 0000-0002-1858-4724.
Under Review
Algorithm XXXX: MQSI – Monotone Quintic Spline Interpolation
Thomas C.H. Lux, Layne T. Watson, William Thacker, Tyler H. Chang. ACM Transactions on Mathematical Software. submitted August, 2020. [code]
Algorithm XXXX: VTMOP: Solver for Blackbox Multiobjective Optimization Problems
Tyler H. Chang, Layne T. Watson, Jeffrey Larson, William Thacker, Shubhangi Deshpande, Thomas C.H. Lux. ACM Transactions on Mathematical Software. submitted May, 2020.
Design Strategies and Approximation Methods for High-Performance Computing Variability Management
Yueyao Wang, Li Xu, Thomas C.H. Lux, Tyler H. Chang, Layne T. Watson, Yili Hong. Journal of Quality Technology. submitted May, 2020.
Published
Prediction of High-Performance Computing Input/Output Variability and Its Application to Optimization for System Configurations
Li Xu, Thomas C.H. Lux, Tyler Chang, Bo Li, Yili Hong, Layne Watson, Ali Butt, Danfeng Yao, Kirk Cameron. . February, 2021. [link]
Interpolation of Sparse High-Dimensional Data
Thomas C.H. Lux, Layne T. Watson, Tyler H. Chang, Yili Hong, Kirk Cameron. Numerical Algorithms, Springer Journal. December, 2020. [pdf] [link]
Algorithm 1012: DELAUNAYSPARSE: Interpolation via a Sparse Subset of the Delaunay Triangulationin Medium to High Dimensions
Tyler H. Chang, Layne T. Watson, Thomas C.H. Lux, Ali R. Butt, Kirk W. Cameron, Yili Hong. ACM Transactions on Mathematical Software. December, 2020. [link] [code]
Thesis: Interpolants, Error Bounds, and Mathematical Software for Modeling and Predicting Variability in Computer Systems
Thomas C.H. Lux. VTechWorks: Digital Library for Virginia Polytechnic Institute and State University. September, 2020. [pdf] [link] [code] [slides]
Analytic Test Functions for Generalizable Evaluation of Convex Optimization Techniques
Thomas C.H. Lux, Tyler H. Chang. Institute of Electrical and Electronics Engineers Southeastcon. January, 2020. [pdf] [link]
Effective Nonparametric Distribution Modeling for Distribution Approximation Applications
Thomas C.H. Lux, Layne T. Watson, Tyler H. Chang, Li Xu, Yueyao Wang, Jon Bernard, Yili Hong, Kirk W. Cameron. Institute of Electrical and Electronics Engineers Southeastcon. January, 2020. [pdf] [link]
An Algorithm for Constructing Monotone Quintic Interpolating Splines
Thomas C.H. Lux, Layne T. Watson, Tyler H. Chang, Li Xu, Yueyao Wang, Yili Hong. Spring Simulation Multiconference, High Performance Computing Symposium. February, 2020. [pdf] [link]
Managing Computationally Expensive Blackbox Multiobjective Optimization Problems with libEnsemble
Tyler H. Chang, Jeffrey Larson, Layne T. Watson, Thomas C.H. Lux. Spring Simulation Multiconference, High Performance Computing Symposium. February, 2020. [link]
Modeling I/O Performance Variability in High-Performance Computing Systems Using Mixture Distributions
Li Xu, Yueyao Wang, Thomas C.H. Lux, Tyler Chang, Bo Li, Kirk Cameron, Layne Watson, Jon Bernard. Journal of Parallel and Distributed Computing. January, 2020. [link]
A Case Study on a Sustainable Framework for Ethically Aware Predictive Modeling
Thomas C.H. Lux, Stefan Nagy, Mohammed Almannaa, Sirui Yao, Reid Bixler. IEEE International Symposium on Technology and Society (ISTAS). December, 2019. [pdf] [link] [video]
Least Squares Solutions to Polynomial Systems of Equations with Quantum Annealing
Thomas C.H. Lux, Tyler H. Chang, Sai Sindhura Tipirneni. Quantum Information Processing, Springer. October, 2019. [pdf] [link] [code]
MOANA: Modeling and Analyzing I/O Variability in Parallel System Experimental Design
Kirk W. Cameron, Ali Anwar, Yue Cheng, Li Xu, Bo Li, Uday Ananth, Jon Bernard, Chandler Jearls, Thomas C.H. Lux, Yili Hong, Layne T. Watson, Ali R. Butt. IEEE Transactions on Parallel and Distributed Systems. January, 2019. [link]
Optimized Drag Reduction and Wake Dynamics Associated with Rotational Oscillations of a Circular Cylinder
A. Mehmood, M.R. Hajj, I. Akhtar, M. Ghommem, L.T. Watson, T.C.H. Lux. Contemporary Engineering Sciences (Hikari | International Publishers). November, 2018. [link]
Prediction for Distributional Outcomes in the Management of High-Performance Computing Input/Output (I/O) Variability (poster)
Li Xu, Thomas C.H. Lux, Tyler Chang, Bo Li, Yili Hong, Layne Watson, Kirk Cameron, Jon Bernard. Joint Statistical Meeting (American Statistical Association). July, 2018. [link]
Nonparametric Distribution Models for Predicting and Managing Computational Performance Variability
Thomas C.H. Lux, Layne T. Watson, Tyler H. Chang, Jon Bernard, Bo Li, Xiaodong Yu, Li Xu, Godmar Back, Ali R. Butt, Kirk W. Cameron, Yili Hong, Danfeng Yao. Institute of Electrical and Electronics Engineers Southeastcon. April, 2018. [pdf] [link]
Computing the Umbrella Neighbourhood of a Vertex in the Delaunay Triangulation and a Single Voronoi Cell in Arbitrary Dimension
Tyler H. Chang, Layne T. Watson, Thomas C.H. Lux, Sharath Raghvendra, Bo Li, Li Xu, Ali R. Butt, Kirk W. Cameron, Yili Hong. Institute of Electrical and Electronics Engineers Southeastcon. April, 2018. [link]
Predictive Modeling of I/O Characteristics in High Performance Computing Systems
Thomas C.H. Lux, Layne T. Watson, Tyler H. Chang, Jon Bernard, Bo Li, Li Xu, Godmar Back, Ali R. Butt, Kirk W. Cameron, Yili Hong. Spring Simulation Multiconference, High Performance Computing Symposium. April, 2018. [pdf] [link]
Predicting System Performance by Interpolation Using a High-Dimensional Delaunay Triangulation
Tyler H. Chang, Layne T. Watson, Thomas C.H. Lux, Jon Bernard, Bo Li, Li Xu, Godmar Back, Ali R. Butt, Kirk W. Cameron, Yili Hong. Spring Simulation Multiconference, High Performance Computing Symposium. April, 2018. [link]
Novel Meshes for Multivariate Interpolation and Approximation
Thomas C.H. Lux, Layne T. Watson, Tyler H. Chang, Jon Bernard, Bo Li, Xiaodong Yu, Li Xu, Godmar Back, Ali R. Butt, Kirk W. Cameron, Danfeng Yao, Yili Hong. Association for Computing Machinery Southeast Conference. March, 2018. [pdf] [link]
A Polynomial Time Algorithm for Multivariate Interpolation in Arbitrary Dimension via the Delaunay Triangulation
Tyler H. Chang, Layne T. Watson, Thomas C.H. Lux, Bo Li, Li Xu, Ali R. Butt, Kirk W. Cameron, Yili Hong. Association for Computing Machinery Southeast Conference. March, 2018. [link]
Teaching Variability in a Core Systems Course (abstract only)
Godmar Back, Lance Chao, Pratik Anand, Thomas C.H. Lux, Bo Li, Ali Butt, Kirk Cameron. Proceedings of the 49th ACM Technical Symposium on Computer Science Education (SIGCSE). February, 2018. [link]
Convergence Rate Evaluation of Derivative Free Optimization Techniques
Thomas C.H. Lux. International Workshop on Machine Learning, Optimization, and Big Data (MOD). September, 2016. [pdf] [link]
Applications of Supervised Learning Techniques on Undergraduate Admissions Data
Thomas C.H. Lux, Randall Pittman, Maya Shende, Anil Shende. ACM International Conference on Computing Frontiers. May, 2016. [pdf] [link]
Projects
fmodpy Automatic Fortran Wrapper for Python
Thomas C.H. Lux. Github. June, 2017-present. [code]
regex Fast regular expression library in C for Python
Thomas C.H. Lux. Github. October, 2020. [code]
sync Lightweight Cross-Device File Synchronization Utility
Thomas C.H. Lux. Github. Jan, 2020. [code]
qaml Quantum Annealing Math Library
Thomas C.H. Lux, Tyler H. Chang, Sai Sindhura Tipirneni. Github. October, 2019. [paper] [code]
Metric Principle Component Analysis: On Identifying Important Subspaces for Approximation
Thomas C.H. Lux, Tyler H. Chang. Github. December, 2018. [paper]
Adversarial Control of Neural Network Policies
Thomas C.H. Lux, Reid Bixler, Colin Shea-Blymyer. Github. November, 2017. [paper]
Optimizing OpenDwarf Applications for CPU and GPU Platforms
Thomas C.H. Lux, Kyle Tanous. Github. May, 2017. [paper]
Education
Virginia Tech
I received my Ph.D. in Computer Science (CS) from Virginia Tech in August 2020. I was co-advised by Dr. Layne T. Watson in CS and Dr. Yili Hong in Statistics. I worked as part of the VarSys research team, applying mathematical models to the study of variability in computation. My primary research area was computational science, specifically numerical analysis and approximation theory. My dissertation is titled Interpolants, Error Bounds, and Mathematical Software for Modeling and Predicting Variability in Computer Systems.
Roanoke College
I received my B.S. in Computer Science with minors in Mathematics and Physics from Roanoke College. I was advised by Dr. Durell Bouchard and did research projects with him in robotics and computer vision; I did research with Dr. Anil Shende on parallel computing and machine learning projects. At Roanoke I was heavily involved in student life and cocurriculars, committing three years (and lots of time) to Student Government and being a Resident Advisor, as well as participating in every club and organization whose meetings I could attend.
Personal
My personal research ambitions outside of my direct experience and dissertation work focus on progress towards artificial general intelligence. My current line of work for this is centered about trying to automatically infer the structure of data in order to build very sample-efficient approximations. For fun, here are some examples of neural network activations at each node for a simple regression problem. These activations were retrieved from my own implementation of a multilayer perceptron in Fortran.
In the process of pursuing structure prediction for AI, I have made a history-based stock futures prediction algorithm. Some sample predictions are available for DOGE and TSLA. I’m working on starting a blog here.
Outside of Computer Science, I like to hike, run, ride motorcycles, and play music. I was originally trained in percussion / drum set for Jazz and I’ve taught myself some guitar and piano for fun on the side. I ventured into positive psychology in college and wrote this summary of Jonathan Haidt’s Happiness Hypothesis, I love that book! Lastly, I enjoy trying to take pretty pictures in my free time and these are some of my favorites.
