VT Statistics and Artificial Intelligence Laboratory (VT-SAIL)


Artificial intelligence (AI) is data-driven in its core. Establishing a rigorous framework for data collection, model training, uncertainty quantification, and safety analysis is critical for AI. Classical statistical concepts, such as population, representativeness of training data, robustness of the learning, and reliability of the algorithm are all very important to ensure AI to be accurate, robust, and safe. The VT-SAIL lab will focus on methodology development of statistics-guided artificial intelligence, especially on data selection, interpretable models, uncertainty quantification, safety analysis, and experimental design thinking for AI assurance.

Faculty

Xinwei Deng, Co-Director, Professor of Statistics, Virginia Tech

Yili Hong, Co-Director, Professor of Statistics, Virginia Tech

Students

Xueying Liu

Xinlei Zhang

Kexin Xie

Hao He

Simin Zheng

Jared Clark

Lina Lee

Xinyi Song

News

(Workshop) IMSI Long Program on Uncertainty Quantification and AI for Complex Systems will be hosted by IMSI at Chicago, IL on March 3 -May 23, 2025.

(October 2024) The AI Reliability Paper won the Soren Bisgaard Award. Congratulations!

(August 2024) VT-SAIL has received a NSF funding on Mathematical Foundations of Quantum Digital Twins. Congratulations!

(June 2024) Jie Min defended her PhD dissertation. Congratulations, Jie!

(May 2024) Qing Guo defended her PhD dissertation. Congratulations, Qing!

(May 2024) Simin Zheng has been recived the best poster award from the DAE 2024 conference. Congratulations, Simin Guo!

(May 2024) VT-SAIL has received a VT Dean's Discovery Funding on AI-Powered Statistical Analysis and Performance Evaluation. Congratulations!

(Conference) Design and Analysis of Experiments Conference 2024 were hosted by Department of Statistics at Virginia Tech on May 15-17, 2024.

(December 2023) VT-SAIL has received a CCI funding on Innovating Supply Chain Security for AI-Assisted Devices. Congratulations!

(July 2023) Jiayi Lian defended his PhD dissertation. Congratulations, Jiayi!

(April 2023) VT-SAIL has received an NSF funding on Modeling and Active Learning of Quantitative-Sequence Experiments. Congratulations!

(Janruary 2023) VT-SAIL has received a CCI funding on Enhancing Human Confidence and Trust in Deep Learning Models. Congratulations!

(Conference) ASA/IMS Spring Research Conference 2023 took place at Banff Center on May 24-26, 2023.

(CFP) Special Issue of “Design and Analysis of Experiments for Data Science” at New England Journal of Statistics in Data Science (NEJSDS)

(September 2022) Qing Guo has been awarded the Amazon Fellowship. Congratulations, Qing Guo!

(August 2022) Yanran Wei defended her PhD dissertation. Congratulations, Yanran!

(June 2022) Yueyao Wang defended her PhD dissertation. Congratulations, Yueyao!

(June 2022) Xinwei Deng has been promoted to the full professor. Congratulations, Xinwei!

(February 2022) Zhihao Hu defended his PhD dissertation. Congratulations, Zhihao!

(Janruary 2022) Yueyao Wang won the ASA SPES+QP Best Student Paper Award. Congratulations, Yueyao!

(Janruary 2022) VT-SAIL has received VT-COS research equipment grant for building flexible small-scale GPU computing power. Congratulations!

(December 2021) Xinwei Deng has been awarded the Data Science Faculty Fellowship. Congratulations, Xinwei!

(June 2021) Li Xu defended his PhD dissertation. Congratulations, Li!

(June 2021) VT-SAIL has received CoVA CCI Cybersecurity research funding for assessment of the federated AI algorithms in cyber-physical systems. Congratulations!

(May 2021) VT-SAIL has received the Commonwealth Cyber Initiative (CCI) funding for experimental research in CCI Testbeds. Congratulations!

(May 2020) Yili Hong has been promoted to the full professor. Congratulations, Yili!

(January 2020) VT-SAIL has received an NSF grant to investigate the robustness of AI algorithms. Congratulations!

(December 2019) Sumin Shen defended his PhD dissertation. Congratulations, Sumin!

(August 2019) Zhongnan Jin defended his PhD dissertation. Congratulations, Zhongnan!

(July 2019) Maggie Mao defended her PhD dissertation. Congratulations, Maggie!

(April 2019) VT-SAIL Lab is launched!

Research Publications

2024

Xu, L., Hong, Y., Morris, M., and Cameron, K. W. (2024). Prediction for Distributional Outcomes in High-Performance Computing Input/Output Variability, Journal of the Royal Statistical Society Series C, in press.

Xu, L., Hong, Y., Smith, E. P., McLeod, D. S., Deng, X., and Freeman, L. J. (2024). Deep Neural Network Identification of Limnonectes Species and New Class Detection Using Image Data, Journal of Agricultural, Biological, and Environmental Statistics, in press.

Kamruzzaman, M., Heavey, J., Song, A., Bielskas, M., Bhattacharya, P., Madden, G., Klein, E., Deng, X., and Vullikanti, A. (2024). Improving Risk Prediction of Methicillin-Resistant Staphylococcus Aureus (MRSA) using Network Features, Journal of Medical Internet Research-AI, in press.

Hu, Z., Liu, X., Deng, X., and Kuhlman, C. J. (2024). An Uncertainty Quantification Framework for Agent-Based Modeling and Simulation in Networked Anagram Games, Journal of Simulation, in press.

He, H., Liu, X., Kuhlman, C. J., and Deng, X. (2024). A Framework of Digital Twins for Modeling Human-Subject Word Formation Experiments, Winter Simulation Conference (WSC 2024), accepted.

Lian, J., Liu, X., Choi, K., Veeramani, B., Hu, A., Freeman, L., Bowen, E., and Deng, X. (2024). Data Composition for Continual Learning in Application of Cyberattack Detection, The International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2024), accepted.

2023

Xiao, Q., Wang, Y., Mandal, A., and Deng, X. (2023). Modeling and Active Learning for Experiments with Quantitative-Sequence Factors, Journal of the American Statistical Association, in press.

Wang, Y., Xu, L., Hong, Y., Pan, R., Chang, T., Lux, T., Bernard, J., Watson, L., and Cameron, K. (2023). Design Strategies and Approximation Methods for High-Performance Computing Variability Management, Journal of Quality Technology , 55, 88-103.

Liu, X., Hu, Z., Kuhlman, C. J. and Deng, X. (2023). Learning Common Knowledge Networks Via Exponential Random Graph Models, 11th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2023) (Acceptance rate 17%).

Shen, S., Mao, H., Zhang, Z., Chen, Z., Nie, K., and Deng, X. (2023). Clustering-based Imputation for Dropout Buyers in Large-scale Online Experimentation, New England Journal of Statistics in Data Science, accepted.

Liu, X., Hu, Z., Deng, X., and Kuhlman, C. J. (2023). A Calibration Model for Bot-Like Behaviors in Agent-Based Anagram Game Simulation, Winter Simulation Conference (WSC 2023), accpeted.

Lian, J., Choi, K., Veeramani, B., Hu, A., Freeman, L., Bowen, E., and Deng, X. (2023). Do-AIQ: A Design-of-Experiment Approach to Quality Evaluation of AI Mislabel Detection Algorithm, Journal of Quality Technology , submitted.

2022

Guo, Q., Chen, J., Wang, D., Yang, Y., Deng, X., Huang J., Carin, L., Tao, C. and Li, F. (2022). Tight Mutual Information Estimation with Contrastive Fenchel-Legendre Optimization, Advances in Neural Information Processing Systems (NeurIPS 2022), accepted.

Hong, Y., Min, J., King, C.B. and Meeker, W. Q. (2022). Reliability Analysis of Artificial Intelligence Systems Using Recurrent Events Data from Autonomous Vehicles, Journal of the Royal Statistical Society Series C (Applied Statistics), in press.

Kenett, R. S., Gotwalt, C., Freeman, L., and Deng, X. (2022). Self-Supervised Cross Validation using Data Generation Structure, Applied Stochastic Models in Business and Industry, accepted.

Hong, Y., Lian, J., Xu, L., Min, J., Wang, Y., Freeman, L., and Deng, X. (2022). Statistical Perspectives on Reliability of Artificial Intelligence Systems, Quality Engineering, accepted.

Liu, X., Hu, Z., Deng, X., and Kuhlman, C. J. (2022). A Bayesian Uncertainty Quantification Approach for Agent-Based Modeling of Networked Anagram Games, Winter Simulation Conference (WSC 2022), in press.

Liu, X., Hu, Z., Deng, X., and Kuhlman, C. J. (2022). Bayesian Approach to Uncertainty Visualization of Heterogeneous Behaviors in Modeling Networked Anagram Games, The International Conference on Complex Networks and their Applications (CNA 2022), in press.

2021

Hu, Z., Deng, X., Kuhlman, C. J. (2021). Versatile Uncertainty Quantification of Contrastive Behaviors for Modeling Networked Anagram Games, The International Conference on Complex Networks and their Applications (CNA 2021), in press.

Hu, Z., Deng, X., Kuhlman, C. J. (2021). An Uncertainty Quantification Approach for Agent-Based Modeling of Human Behavior in Networked Anagram Games, Winter Simulation Conference (WSC 2021), in press.

Shojaee, P., Zeng, Y., Chen, X., Jin, R., Deng, X., and Zhang, C. (2021). Deep Neural Network Pipelines for Multivariate Time Series Classification in Smart Manufacturing, The 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS), in press.

Cai, X., Xu, L., Lin, C. D., Hong, Y., and Deng, X. (2021). Sequential Design of Computer Experiments with Quantitative and Qualitative Factors in Applications to HPC Performance Optimization, SIAM Journal of Uncertainty Quantification, revision submitted.

2020

Lian, J., Freeman, L., Hong, Y., and Deng, X. (2020). Investigating the Robustness of Artificial Intelligent Algorithms with Mixture Experiments, Journal of Quality Technology, submitted.

Xie, W., and Deng, X. (2020). Scalable Algorithms for the Sparse Ridge Regression, SIAM Journal on Optimization, in press.

Xu, L., Wang, Y., Lux, T., Chang, T., Bernard, J., Li, B., Hong, Y., Watson, L., and Cameron, K. (2020). Modeling I/O Performance Variability in High-Performance Computing Systems using Mixture Distributions, Journal of Parallel and Distributed Computing, 139, 87-98.

Mao, H., Deng, X., Jiang, H., Shi, L., Li, H., Tuo, L., and Guo, F. (2020). Driving Safety Assessment for Ride-hailing Drivers, Accident Analysis and Prevention, in press.

Kang, X., Chen, X., Jin, R., Wu, H., and Deng, X. (2020). Multivariate Regression of Mixed Responses for Evaluation of Visualization Designs, IISE Transactions, in press.

2019

Xie, Y., Xu L., Li, J., Deng, X., Hong, Y., and Kolivras, K. N. (2019). Spatial Variable Selection via Elastic Net with an Application to Virginia Lyme Disease Case Data, Journal of the American Statistical Association, 114(528), 1466-1480.

Cedeno-Mieles, V., Hu, Z., Deng, X., Ren, Y., et al. (2019). Networked Experiments and Modeling for Producing Collective Identity in a Group of Human Subjects Using an Iterative Abduction Framework, Social Network Analysis and Mining, 10, 11.

Cameron, K., Anwar, A., Cheng, Y., Xu, L., Li, B., Ananth, U., Bernard, J., Jearls, C., Lux, T., Hong, Y., Watson, L., and Butt, A. (2019). MOANA: Modeling and Analyzing HPC I/O Variability, IEEE Transactions on Parallel and Distributed Systems, 30(8), 1843-1856.

Shen, S., Zhang, Z., and Deng, X. (2019). On Design and Analysis of Funnel Testing Experiments in Webpage Optimization, Journal of Statistical Theory and Practice, 14, 3.

Cedeno-Mieles, V., Hu, Z., Deng, X., Ren, Y., et al. (2019). Mechanistic and Data-Driven Agent-Based Models to Explain Human Behavior in Web-Based Group Anagrams Games, 11th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2019) (Acceptance rate 14%).

2018

Cadena, J., Basak, A., Vullikanti, A., and Deng, X. (2018). Graph Scan Statistics with Uncertainty, 32nd AAAI Conference on Artificial Intelligence (AAAI-18), 2771-2778. (Acceptance rate 25%).

Ren, Y., Cedeno-Mieles, V., Hu, Z., Deng, X., et al. (2018). Generative Modeling of Human Behavior and Social Interactions Using Abductive Analysis, 10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2018), 413-420. (Acceptance rate 15%).

Blog

Here is a blog of Data Thinking at VT.

Copyright © VT-SAIL 2024