SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data — mentioned by stochastic_monk

Mon, 13 Nov 2017 02:51:43 GMT

You're correct. Boosting was directly formulated in the PAC framework. (Source: http://l2r.cs.uiuc.edu/Teaching/CS446-17/LectureNotesNew/boo... "The original boosting algorithm was proposed as an answer to a theoretical question in PAC learning [The Strength of Weak Learnability; Schapire, 89.]") It took a while, but there's been a lot of work lately explaining neural nets' performance over the last 5 years of so, from papers showing PAC learnability for specific architectures (https://arxiv.org/abs/1710.10174) to work saying that most local optima are close to global optima…

Paper and discussion history. A mention is not an endorsement.

SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data · HackerPapers discussions

SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data — mentioned by stochastic_monk