Two faces of active learning

By Sanjoy Dasgupta. Theoretical Computer Science, 2011

336 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e1f3ba9deb6c85f9cb47bf6227b254f0a3e3681a

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

Citations in the corpus

On the calibration of sensor arrays for pattern recognition using the minimal number of experiments (2014, result): “Moreover, the uniform distribution of the data with respect to the concentration c makes the results unbiased [53].”
Active Imitation Learning via Reduction to I.I.D. Active Learning (2012, background): “In the agnostic case, it has been shown that exponential improvement in label complexity with respect to 1 is achievable when infπ∈H ef (π,DX ) is relatively small compared to (Dasgupta 2011).”
The strategic student approach for life-long exploration and learning (2012, background): “1Formal study of active learning in general is also quite recent [15], [16].”
A Survey of Deep Active Learning (2020, background): “Because separate sampling based on uncertainty often results in sampling bias [31], the currently selected sample is not representative of the distribution of unlabeled datasets.”
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds (2019, background): “Active learning is a been well-studied problem (Settles, 2010; Dasgupta, 2011; Hanneke, 2014).”
Toward Minimax Off-policy Value Estimation (2015, background): “We also discuss the implications of these results for off-policy evaluation problems in contextual bandits and fixed-horizon Markov decision processes.”
Generative Adversarial Active Learning (2017, background): “For an introduction to active learning, readers are referred to (Settles, 2010; Dasgupta, 2011).”