Statistics Seminar - 08/29/24

Aug 29 3:40 pm

Dr. Jin Lu, Assistant Professor, School of Computing, University of Georgia


Statistics Seminar Series


Harnessing Provable Algorithms for Machine Learning in the Wild: Mobilizing, transferring, and Adaptive Morphing

Physical Location

Allen 411


Amidst increasing data volumes, addressing large-scale machine learning challenges in environments characterized by inherent variability is crucial. Such variability impacts data collection, format, quality, computational capacity, and connectivity within cyber-physical systems, thereby shaping the development of resilient machine learning models across a wide array of high-impact applications.  In dynamic environments, variability can manifest in several ways: (1) evolving network settings, with continuously changing topologies and reliability; (2) heterogeneous data sources and formats, featuring diverse data sample resources and formats as supplementary information; (3) limited computational power, where constraints and disparities in computational capacity hinder extensive model training and exacerbate unfairness.

This presentation will focus on environmental variability, highlighting recent efforts to develop theoretically robust machine learning approaches addressing these challenges with provable guarantees. The goal is to improve learning models by adapting them to adverse environments. We will examine three core methodological directions—mobilizing, transferring, and adaptive morphing—alongside case studies, including federated learning and mobile health.



Dr. Jin Lu is an assistant professor at the School of Computing at the University of Georiga, His major research interests include machine learning, data mining, optimization, smart mobility, biomedical informatics, and health informatics. He is particularly interested in transparent machine learning models, high-performance algorithms, and interpretable methods for critical scientific and engineering problems.

Dr. Jin Lu has been working on Data Science, Machine Learning, Optimization, and Intelligent Systems areas for over 8 years. His research has been published in top-tier journals and conference proceedings including International Conference on Machine Learning (ICML), Annual Conference on Neural Information Processing Systems (NeurIPS), IEEE International Conference on Mobile Ad-hoc and Sensor Systems (MASS), BMC Journal of Systems Biology, IEEE Transactions on Big Data, ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp), IEEE Proceedings of Ubiquitous Intelligence and Computing (UIC), Proceedings of the IEEE International Conference on Big Data, Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE Annual Computing and Communication Workshop and Conference, Conference on Neural Information Processing Systems (NIPS), Sedimentology, IEEE Wireless Health (WH), Proceedings of IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE).