Biography
I am currently a Postdoc working with Robert Nowak at the University of Wisconsin. Previously, I was a Postdoc at the Paul G. Allen School of Computer Science & Engineering at the University of Washington under Kevin Jamieson. I completed my PhD in the Electrical Engineering and Computer Science Department at the University of Michigan where my advisor was Prof. Clayton Scott. Prior to that, I double-majored in mathematics and philosophy at the University of Chicago. My research focuses on pure exploration multi-armed bandits, recommender systems, and nonparametric estimation. I am also interested in applications of machine learning that promote the social good. As a Data Science for Social Good fellow at the University of Chicago in 2015, I helped develop the Legislative Influence Detector.
Preprints
- Andrew Wagenmaker, Julian Katz-Samuels, Kevin Jamieson. Experimental Design for Regret Minimization in Linear Bandits, accepted to AISTATS 2021.
Publications
- Julian Katz-Samuels, Lalit Jain, Zohar Karnin, Kevin Jamieson. An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits, NeurIPS 2020.
- J. Katz-Samuels, and K. Jamieson. The True Sample Complexity of Identifying Good Arm. AISTATS 2020.
- J. Katz-Samuels, and C. Scott. Top Feasible Arm Identification. AISTATS 2019.
- J. Katz-Samuels, G. Blanchard, and C. Scott. Decontamination of Mutual Contamination Models. Journal of Machine Learning Research 2019.
- J. Katz-Samuels, and C. Scott. Feasible Arm Identification. ICML 2018 (Long Oral Talk).
- J. Katz-Samuels, and C. Scott. Nonparametric Preference Completion. AISTATS 2018.
- Burgess, Matthew, Eugenia Giraudy, Julian Katz-Samuels, Joe Walsh, Derek Willis, Lauren Haynes, and Rayid Ghani. "The Legislative Influence Detector: Finding Text Reuse in State Legislation." In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 57-66. ACM, 2016.
Contact
katzsamuels “at” wisc.edu