69 citations · 336 across the 41 of their papers we have counts for
Showing 2013Show all
3 papers · 1 filter
cs.LG2013★ 34 cited
More data speeds up training time in learning halfspaces over sparse vectors
Amit Daniely, Nati Linial, Shai Shalev Shwartz
The increased availability of data in recent years has led several authors to ask whether it is possible to use data as a {\em computational} resource. That is, if more data is ava…
cs.LG2013★ 6 cited
From average case complexity to improper learning complexity
Amit Daniely, Nati Linial, Shai Shalev-Shwartz
The basic problem in the PAC model of computational learning theory is to determine which hypothesis classes are efficiently learnable. There is presently a dearth of results showi…
cs.LG2013★ 2 cited
The price of bandit information in multiclass online classification
Amit Daniely, Tom Helbertal
We consider two scenarios of multiclass online learning of a hypothesis class . In the {\em full information} scenario, the learner is exposed to instances together…