Adaptive Sequential Learning with Applications to Crowdsourcing
- Topic: Adaptive Sequential Learning with Applications to Crowdsourcing
- Speaker: Prof. Xi Chen
- Date: 14:00-15:00 , Tuesday, July 24, 2018
- Venue: Boardroom, Dao Yuan Building
- Abstract
In this talk, we consider a general online learning and decision-making problem, where the goal is to estimate the underlying model parameters in a sequential setup. Our problem is motivated by crowdsourcing applications. In particular, we consider both crowdsourced binary classification and crowd ranking problems, where the decision-maker needs to decide which worker (or which pair of objects) for labeling and when to stop collecting labels to save for budget.
For the binary labeling tasks, we propose an adaptive sequential probability ratio test method (Ada-SPRT), which obtains the optimal worker selection rule, the optimal stopping time, and the optimal decision rule under a unified Bayesian decision framework. For crowd ranking, due to the complex structure, the optimal ranking policy is hard to compute. To address this challenge, we develop an asymptotically optimal ranking policy that achieves the minimal Bayes risk as the sample size goes to infinity. The proposed methods can be applied a wide range of online learning problems, where there is a need for balancing the quality of the solution and the cost of collecting data.
- Biography
Xi Chen is an assistant professor at Stern School of Business at New York University. Before that, he was a Postdoc in the group of Prof. Michael Jordan at UC Berkeley. He obtained his Ph.D. from the Machine Learning Department from CMU.
He studies sequential analysis and multi-armed bandits, and high-dimensional statistical inference under computational constraints. He also works on OR/OM problems, such as data-driven revenue management, and process flexibility. He received Simons-Berkeley Research Fellowship, Google Faculty Research Award, Adobe Data Science Research Award, Alibaba Innovation Award, Bloomberg Data Science Award, and was featured in 2017 Forbes list of “30 Under30 in Science”.
