Ethan X. Fang is an Assistant Professor of Biostatistics & Bioinformatics at Duke Medical School and affiliated with Decision Sciences of Fuqua Business School and Rhodes Information Initiative at Duke University. He works on different data science problems from computational and statistical perspectives. Before joining Duke, he was an assistant professor of Statistics at Penn State. He got his PhD from Princeton University under the direction of Han Liu and Robert Vanderbei, and got his Bachelor’s degree from National University of Singapore under the direction of Kim-Chuan Toh. His works have appeared at top venues in different areas such as statistics, optimization, machine learning, and operations research. He received 2016 Best Paper Prize in Continuous Optimization for Young Researchers (1 paper selected in 3 years).
| Venue | BIZ1 – 0204 |
| Link to Register | https://forms.office.com/r/WgcFdUQQYW |
| Title | Inference for Ranking Problems |
| Abstract | We propose a novel combinatorial inference framework to conduct general uncertainty quantification in ranking problems. We consider the widely adopted Bradley-Terry-Luce (BTL) model, where each item is assigned a positive preference score that determines the Bernoulli distributions of pairwise comparisons’ outcomes. Our proposed method aims to infer the general ranking properties of the BTL model. The general ranking properties include the “local” properties such as if an item is preferred over another and the “global” properties such as if an item is among the top K-ranked items. We further generalize our inferential framework to multiple testing problems where we control the false discovery rate (FDR) and apply the method to infer the top-K ranked items. We also derive the information-theoretic lower bound to justify the minimax optimality of the proposed method. We conduct extensive numerical studies using both synthetic and real data sets to back up our theory. |
You may contact WONG Cecilia/TAN Dorothy at 6516 6225/6516 3067 for enquiries.
