PAC learning with noise

cosmos 10th April 2019 at 10:58am
Probably approximately correct

See https://arxiv.org/pdf/math/0702683.pdf and http://www.stats.ox.ac.uk/~rebeschi/teaching/AFoL/18/

Work of Tsybako and Massart

http://papers.nips.cc/paper/5073-learning-with-noisy-labels.pdf – The case where there is noise on the training data, but not on the test data!