Students, faculty, and staff are invited to attend the upcoming event in the Mathematics and Statistics Seminar Series with speaker Dr. Bernhard Spangl on Tuesday, November 11, from 1:00 PM to 2:00 PM. The talk is entitled Active learning: blending design of experiments and supervised learning
Abstract
In this talk I will focus on two research topics: (i) sample size estimation in balanced ANOVA models and (ii) query-by-committee active learning in regression scenarios. Their common aim is to minimize the sample size.
First, we consider balanced one-way, two-way, and three-way ANOVA models to test the hypothesis that the fixed factor A has no effect. The other factors are fixed or random. We determine the noncentrality parameter for the exact F-test, describe its minimal value by a sharp lower bound, and thus we can guarantee the worst-case power for the F-test. These results allow us to compute the minimal sample size, i.e. the minimal number of experiments needed. Additionally, we provide a structural result for the minimal sample size that we call “pivot” effect (cf. also Spangl et al., 2021).
Second, we discuss the problem of active learning in regression scenarios. In active learning, the goal is to provide criteria that the learning algorithm can employ to improve its performance by actively selecting data that are most informative. Active learning is usually thought of as being a sequential process where the training set is augmented one data point at a time. We restrict ourselves to a pool-based sampling scenario and investigate a committee-based approach as query strategy for actively selecting instantiations of the input variables x that should be labelled and incorporated into the training set using a real chemometric data set.
Registration link
