Learning from partial correction

We introduce a new model of interactive learning in which an expert examines the predictions of a learner and partially fixes them if they are wrong. Although this kind of feedback is not i.i.d., we show statistical generalization bounds on the quality of the learned model.

[1]  D. Angluin.  Queries and Concept Learning , 1988 .

[2]  Maria-Florina Balcan,et al.  Clustering with Interactive Feedback , 2008, ALT.

[3]  Burr Settles,et al.  Active Learning , 2012, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[4]  Maria-Florina Balcan,et al.  Local algorithms for interactive clustering , 2013, ICML.

[5]  David Kempe,et al.  A General Framework for Robust Interactive Learning , 2017, NIPS.

[6]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.