Upper and Lower Error Bounds for Active Learning

By Rui M. Castro, Robert D. Nowak. 2006

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Stefano Teso
2. Maya Cakmak
3. Kristian Kersting
4. Andrea Lockerd Thomaz
5. Steve Hanneke
6. Maria-Florina Balcan
7. Sanjoy Dasgupta
8. Sriraam Natarajan

Citations in the corpus

• Rates of convergence in active learning (2011, background): “For any hypothesis class”
• Explanatory Interactive Machine Learning (2019, background): “By carefully selecting the instances to be labelled, active learning can enjoy much better sample complexity than passive learning [2, 6].”
• Mixed-Initiative Active Learning (2012, result): “Although theoretical results supporting the benefits of AL have been limited (Castro & Nowak, 2006; Balcan et al., 2010), many papers published over that last decade have demonstrated the practical strength of AL with human oracles (Settles, 2010).”