The true sample complexity of active learning

By Maria-Florina Balcan, Steve Hanneke, Jennifer Wortman Vaughan. 2010

190 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

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

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

The power of localization for efficiently learning linear separators with noise (2013, background): “…active learning, and several general characterizations have been developed for describing when active learning could have an advantage over the classic passive supervised learning paradigm both in the noise free settings and in the agnostic case [24, 20, 3, 4, 28, 22, 17, 7, 36, 11, 43, 21, 38, 6].”
Towards more Reliable Transfer Learning (2018, methodology): “ reliability. Active learning: At the other end of the spectrum, active learning has been proven to be eective both empirically and theoretically. A new denition of sample complexity is proposed in [1] to show that active learning is strictly better than passive learning asymptotically. In recent ye”
Two faces of active learning (2011, background): “A series of recent papers [4, 14] analyzes such cases by loosening the definition of disagreement coefficient from”
Crowdsourcing large scale wrapper inference (2014, background): “Active learning techniques [34] have recently gained interest as they can produce exponential improvements over the number of samples with respect to traditional supervised approaches [4].”
Active Learning and Intrinsically Motivated Exploration in Robots : Advances and Challenges (2010, background): “It has been proved that, under mild conditions, an active learner outperforms a passive learner [6], [17], provided that we have some information on the structure of the problem, even when we cannot estimate in advance that improvement [18].”
Importance weighted active learning (2008, background): “These experiments suggest that IWAL is a practically useful realization of the theoretical claim that active learning can reduce the label complexity without compromising prediction performance or safety compared to passive learning[4].”
Active and passive learning of linear separators under log-concave distributions (2012, background): “…(Dasgupta, 2011), with many exciting developments on understanding its underlying principles as well (Freund et al., 1997; Dasgupta, 2005; Balcan et al., 2006, 2007; Hanneke, 2007; Dasgupta et al., 2007; Castro and Nowak, 2007; Balcan et al., 2008; Koltchinskii, 2010; Beygelzimer et al., 2010).”
Active Learning Literature Survey (2009, background): “However, Balcan et al. (2008) also show that, under an asymptotic setting, active learning is always better than supervised learning in the limit.”
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).”
A compression technique for analyzing disagreement-based active learning (2014, unknown): “…Hanneke, 2007a; Dasgupta, Hsu, and Monteleoni, 2007; Balcan, Broder, and Zhang, 2007; Beygelzimer, Dasgupta, and Langford, 2009; Friedman, 2009; Balcan, Hanneke, and Vaughan, 2010; Hanneke, 2011; Koltchinskii, 2010; Beygelzimer, Hsu, Langford, and Zhang, 2010; Hsu, 2010; Hanneke, 2012;…”
Rates of convergence in active learning (2011, background): “See [8, 10, 14, 16, 19, 33] for further discussions of various uses of the disagreement coefficient and related notions and extensions in active learning.”
Guest Editorial Active Learning and Intrinsically Motivated Exploration in Robots: Advances and Challenges (2010, background): “It has been proved that, under mild conditions, an active learner outperforms a passive learner [6], [17], provided that we have some information on the structure of the problem, even when we cannot estimate in advance that improvement [18].”