NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:2659
Title:Distribution-Independent PAC Learning of Halfspaces with Massart Noise

This is a very strong paper that makes impressive progress on the long-standing open problem of efficiently PAC learning halfspaces under the Massart noise model. While resolving the problem would involve getting within epsilon of the optimal error, achieving eta + epsilon is a breakthrough and likely will fuel future results in learning theory.