August 28, 2017
Steve Hanneke Wins Honorable Mention for 2017 ICML Test of Time Award
Congratulations to MLD alumnus Steve Hanneke for winning an Honorable Mention for the 2017 International Conference on Machine Learning (ICML) Test of Time Award. Hanneke's paper, A Bound on the Label Complexity of Agnostic Active Learning, is from his work as a PhD student in the Machine Learning Department and it is a solo-author student paper.
Paper Abstract: We study the label complexity of pool-based active learning in the agnostic PAC model. Specifically, we derive general bounds on the number of label requests made by the A^2 algorithm proposed by Balcan, Beygelzimer & Langford (2006). This represents the first nontrivial general-purpose upper bound on label complexity in the agnostic PAC model.