Optimally-Smooth Adaptive Boosting and Application to Agnostic Learning

45 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

On agnostic boosting and parity learning (2008, background): “In subsequent work, Gavinsky [6] showed that such a learner can be boosted to achieve error ≤ opt 1 / 2 − β + (cid:15) and gave a lower-bound oﬀ by a factor of 2.”
Attribute-efficient learning of decision lists and linear threshold functions under unconcentrated distributions (2006, methodology): “The booster proposed by Gavinsky might set all of these weights to zero: in such cases, it was terminated.”
Distribution-Specific Agnostic Boosting (2009, methodology): “In Section 3.2 we use our boosting algorithm to extend the observation that agnostic learning of a class C implies PAC learning of low-weight linear thresholds of functions from C [25, 9, 28] to a distribution speciﬁc setting.”