A General Agnostic Active Learning Algorithm

By Sanjoy Dasgupta, Daniel J. Hsu, Claire Monteleoni. International Symposium on Artificial Intelligence and Mathematics, 2007

334 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/83f0378dc81c5d941c82852e9261d10ea46f8773

How researchers see this paper

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

Citations in the corpus

Hierarchical sampling for active learning (2008, background): “Indeed, there are canonical examples in which active learning provably yields exponentially lower label complexity than supervised learning (Cohn et al., 1994; Freund et al., 1997; Dasgupta, 2005; Balcan et al., 2006; Balcan et al., 2007; Castro & Nowak, 2007; Hanneke, 2007; Dasgupta et al., 2007).”
A compression technique for analyzing disagreement-based active learning (2014, methodology): “…approach, initiated by Cohn, Atlas, and Ladner (1994), and further advanced in numerous articles (e.g., Balcan, Beygelzimer, and Langford, 2009; Dasgupta, Hsu, and Monteleoni, 2007; Beygelzimer, Dasgupta, and Langford, 2009; Beygelzimer, Hsu, Langford, and Zhang, 2010; Koltchinskii, 2010;…”
Scaling Up Crowd-Sourcing to Very Large Datasets: A Case for Active Learning (2014, methodology): “table exceptions are [12] and its IWAL variant [6]; they are blackbox but do not support batching or parallelism.”
The Relationship Between Agnostic Selective Classification Active Learning and the Disagreement Coefficient (2017, methodology): “We use a uniform convergence bound from [24, 29].”
Agnostic active learning (2006, methodology): “In addition, Dasgupta, Hsu, and Monteleoni [ 23 ] introduce and analyze a new agnostic active learning algorithm.”
Agnostic Selective Classification (2011, methodology): “A similar technique of using an ERM oracle that can enforce an arbitrary number of example-based constraints was used in [13, 14] in the context of active learning.”
Crowdsourced Data Management: Industry and Academic Perspectives (2015, background): “Papers focusing on the theory of active learning [56, 64, 111, 31, 92, 38, 37, 28, 63, 198, 136] show that the adaptive selection strategies proposed (i.”
The true sample complexity of active learning (2010, background): “In particular, the most concrete noteworthy positive resul t for when active learning helps is that of learning homogeneous (i.e., through the origin) linear separators, when the data is linearly separable and distributed uniformly ov er the unit sphere, and this example has been extensively analyze”
Efficient and Parsimonious Agnostic Active Learning (2015, methodology): “Under much weaker assumptions, streaming-based agnostic active learning [Balcan et al., 2006, Beygelzimer et al., 2009, 2010, Dasgupta et al., 2007, Zhang and Chaudhuri, 2014] is particularly appealing since it is known to work for any classifier representation and any label noise distribution with…”
Importance weighted active learning (2008, background): “1 Experiments Recent consistent active learning algorithms [3, 9] have su ffered from problems of computational intractability.”
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].”
Active Learning Literature Survey (2009, methodology): “Hanneke (2007) extends this work by providing upper bounds on query complexity for the agnostic setting, and Dasgupta et al. (2008) propose a somewhat more efﬁcient query selection algorithm.”
Active and passive learning of linear separators under log-concave distributions (2012, methodology): “…(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).”
Two faces of active learning (2011, methodology): “Two recent papers, ﬁrst [2] and then [12], have shown how to overcome these hurdles.”
Active Learning as Non-Convex Optimization (2009, background): “Previous work in active learning has shown that active learning can give provably better label complexity than passive learning under certain distribution assumptions (Balcan et al., 2006; Dasgupta et al., 2007, 2005).”
Rates of convergence in active learning (2011, methodology): “See [4, 5, 10, 12, 14] for further discussions of various uses of the disagreement coefficient and related notions and extensions in active learning.”