LGMay 23, 2017
Learning from partial correction
arXiv:1705.08076v44 citations
AI Analysis
This addresses the challenge of learning from non-standard feedback in interactive settings, though it appears incremental as it builds on existing interactive learning frameworks.
The paper tackles the problem of interactive learning where an expert partially corrects learner predictions, showing statistical generalization bounds for the learned model despite non-i.i.d. feedback.
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.