COLT
2007
Springer
15 years 10 months ago
2007
Springer
129
click to vote
COLT
2007
Springer
15 years 10 months ago
2007
Springer
In the standard model of observational learning, n agents sequentially decide between two alternatives a or b, one of which is objectively superior. Their choice is based on a stoc...
148
click to vote
COLT
2007
Springer
15 years 10 months ago
2007
Springer
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 ...
126
click to vote
COLT
2007
Springer
15 years 10 months ago
2007
Springer
Recently, Balcan and Blum [1] suggested a theory of learning based on general similarity functions, instead of positive semi-definite kernels. We study the gap between the learnin...
154
click to vote
COLT
2007
Springer
15 years 10 months ago
2007
Springer
Bounded parameter Markov Decision Processes (BMDPs) address the issue of dealing with uncertainty in the parameters of a Markov Decision Process (MDP). Unlike the case of an MDP, t...
120
click to vote
COLT
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. We establish a generic theoretical tool to construct probabilistic bounds for algorithms where the output is a subset of objects from an initial pool of candidates (or mo...
80
Voted
COLT
2007
Springer
15 years 10 months ago
2007
Springer
119
click to vote
COLT
2007
Springer
15 years 10 months ago
2007
Springer
For the natural notion of splitting classes into two disjoint subclasses via a recursive classifier working on texts, the question is addressed how these splittings can look in th...
119
click to vote
COLT
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. We consider the problem of learning an acyclic discrete circuit with n wires, fan-in bounded by k and alphabet size s using value injection queries. For the class of tran...