Dec 11, 2019

We study the problem of {\em distribution-independent} PAC learning of halfspaces in the presence of Massart noise. Specifically, we are given a set of labeled examples (\bx,y) drawn from a distribution \D on \Rd+1 such that the marginal distribution on the unlabeled points \bx is arbitrary and the labels y are generated by an unknown halfspace corrupted with Massart noise at noise rate η<1/2. The goal is to find a hypothesis h that minimizes the misclassification error \pr(\bx,y)∼\D[h(\bx)≠y]. We give a \poly(d,1/\eps) time algorithm for this problem with misclassification error η+\eps. We also provide evidence that improving on the error guarantee of our algorithm might be computationally hard. Prior to our work, no efficient weak (distribution-independent) learner was known in this model, even for the class of disjunctions. The existence of such an algorithm for halfspaces (or even disjunctions) has been posed as an open question in various works, starting with Sloan (1988), Cohen (1997), and was most recently highlighted in Avrim Blum's FOCS 2003 tutorial.

Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.

Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

Presentations on similar topic, category or speaker