Learning geometric concepts with nasty noise
STOC '18: Symposium on Theory of Computing Los Angeles CA USA June, 2018, pp. 1061-1073, 2018.
We study the efficient learnability of geometric concept classes — specifically, low-degree polynomial threshold functions (PTFs) and intersections of halfspaces — when a fraction of the training data is adversarially corrupted. We give the first polynomial-time PAC learning algorithms for these concept classes with dimension-independent...More
Full Text (Upload PDF)
PPT (Upload PPT)