
My research focuses on compressed sensing, machine learning, signal processing, and the interaction between mathematics, computer science and software engineering. My interests range from theoretical results to algorithms for tackling practical applied problems, and I enjoy problems most when mathematical results lead to efficient software implementations for big data. I am looking forward to working with students at all levels and backgrounds who share an interest in mathematics, software, or data. Some problems that have captured my interest include network analysis for cyber defense, and signal processing and inference for arrays of chemical sensors. In my spare time I enjoy fencing, hiking, skiing, tennis, computer games, and spending time with my family!
Visit Digital WPI to view student projects advised by Professor Paffenroth
Sustainable Development Goals




Research Interests
Scholarly Work
Professor Paffenroth's research focuses on is focused on applications of mathematically principled machine learning techniques to problems in several application domains including manufacturing, chemical sensors, cyber-defense, chemical engineering, and nanomaterials.
Featured works:
Cheng, F., Belden, E. R., Li, W., Shahabuddin, M., Paffenroth, R. C., & Timko, M. T. (2022). Accuracy of predictions made by machine learned models for biocrude yields obtained from hydrothermal liquefaction of organic wastes.Chemical Engineering Journal, 442, . https://doi.org/10.1016/j.cej.2022.136013
Bahadur, N., Lewandowski, B., and Paffenroth, R. (2022). Dimension Estimation Using Autoencoders and Application.Deep Learning Applications, (3rd ed.). Springer Nature.
Mahindre, Karkare, R., Paffenroth, R., & Jayasumana, A. (2021, December 15-18). A Pre-training Oracle for Predicting Distances in Social Networks. 2021 IEEE International Conference on Big Data (Big Data), 4126–4135. https://doi.org/10.1109/BigData52589.2021.9671784
Zhou, C., Paffenroth, R.C. (2017, August 13-17). Anomaly detection with robust deep autoencoders. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 665-674. https://doi.org/10.1145/3097983.3098052
Professional Affiliations
News
Media Coverage
In the article, “WPI Awarded $3M for Graduate Data Program” the Worcester Business Journal reported on WPI using a $3 million grant from the National Science Foundation (NSF) to establish a unique graduate curriculum to train the next generation of scientists who can apply chemical sciences along with data analytics, mathematics, and computing power to reduce energy usage, waste, and pollution. Elke Rundensteiner, professor of computer science, founding director of the Data Science program, and principal investigator on the grant, is collaborating with Michael Timko and Aaron Deskins, associate professors of chemical engineering, and Randy Paffenroth, associate professor of mathematical and data sciences, among others.
Randy Paffenroth, associate professor of mathematical sciences, computer science, and data science, told Boston-based WBZ radio how he is helping the U.S. Army create a thumbnail-sized chemical sensor to protect soldiers. In the five-minute segment, he noted that he is using a “combination of classic and new math to extract from these many sensors what’s in the environment.”