Sciweavers

73 search results - page 4 / 15
» The Complexity of Learning Concept Classes with Polynomial G...
Sort
View
FOCS
2008
IEEE
14 years 2 months ago
What Can We Learn Privately?
Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept ...
Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi ...
COLT
2006
Springer
13 years 11 months ago
DNF Are Teachable in the Average Case
We study the average number of well-chosen labeled examples that are required for a helpful teacher to uniquely specify a target function within a concept class. This "average...
Homin K. Lee, Rocco A. Servedio, Andrew Wan
ATAL
2006
Springer
13 years 11 months ago
Learning to identify winning coalitions in the PAC model
We consider PAC learning of simple cooperative games, in which the coalitions are partitioned into "winning" and "losing" coalitions. We analyze the complexity...
Ariel D. Procaccia, Jeffrey S. Rosenschein
COLT
2007
Springer
14 years 1 months ago
A Lower Bound for Agnostically Learning Disjunctions
We prove that the concept class of disjunctions cannot be pointwise approximated by linear combinations of any small set of arbitrary real-valued functions. That is, suppose there ...
Adam R. Klivans, Alexander A. Sherstov
CC
2010
Springer
120views System Software» more  CC 2010»
13 years 5 months ago
Lower Bounds for Agnostic Learning via Approximate Rank
We prove that the concept class of disjunctions cannot be pointwise approximated by linear combinations of any small set of arbitrary real-valued functions. That is, suppose that t...
Adam R. Klivans, Alexander A. Sherstov