Biography

I am a postdoc working with Robert Nowak at the University of Wisconsin, and was previously a postdoc at the Paul G. Allen School of Computer Science & Engineering at the University of Washington under Kevin Jamieson. I completed my Ph.D. in the electrical and computer engineering at the University of Michigan under Clayton Scott and received my B.A. in mathematics and philosophy at the University of Chicago.

My research focuses on designing practical machine learning algorithms that adaptively collect data to accelerate learning. My recent research interests include active learning, multi-armed bandits, and black-box optimization. I am also very interested in machine learning applications that promote the social good. As a fellow at Data Science for Social Good (University of Chicago), I helped develop the Legislative Influence Detector.

I’m on the job market this year! Feel free to reach out if you think I’d be a good fit for a position!

Preprints

Publications

• Near Instance Optimal Model Selection for Pure Exploration Linear Bandits. Y. Zhu, J. Katz-Samuels, R. Nowak. AISTATS 2022.
• Similarity Search for Efficient Active Learning and Search of Rare Concepts. C. Coleman, E. Chou, J. Katz-Samuels, S. Culatana, P. Bailis, A. C. Berg, R. Nowak, R. Sumbaly, M. Zaharia, I. Zeki Yalniz. AAAI 2022.
• Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers. J. Katz-Samuels, B. Mason, K. Jamieson, R. Nowak. NeurIPS 2021.
• Improved Algorithms for Agnostic Pool-based Active Classification. J. Katz-Samuels, J. Zhang, L. Jain, K. Jamieson. ICML 2021.
• High-Dimensional Experimental Design and Kernel Bandits. R. Camilleri, J. Katz-Samuels, K. Jamieson. ICML 2021 (Long Talk).
• Experimental Design for Regret Minimization in Linear Bandits. A. Wagenmaker, J. Katz-Samuels, K. Jamieson. AISTATS 2021.
• An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits. J. Katz-Samuels, L. Jain, Z. Karnin, K. Jamieson. NeurIPS 2020.
• The True Sample Complexity of Identifying Good Arm. J. Katz-Samuels, K. Jamieson. AISTATS 2020.
• Top Feasible Arm Identification. J. Katz-Samuels, C. Scott. AISTATS 2019.
• Decontamination of Mutual Contamination Models. J. Katz-Samuels, G. Blanchard, C. Scott. Journal of Machine Learning Research 2019.
• Feasible Arm Identification. J. Katz-Samuels, C. Scott. ICML 2018 (Long Talk).
• Nonparametric Preference Completion. J. Katz-Samuels, C. Scott. AISTATS 2018.
• The Legislative Influence Detector: Finding Text Reuse in State Legislation. M. Burgess, E. Giraudy, J. Katz-Samuels, J. Walsh, D. Willis, L. Haynes, R. Ghani. KDD 2016.

Contact

katzsamuels “at” wisc.edu