388 search results - page 53 / 78 » The covering number in learning theory |
SIAMCOMP
2011
13 years 2 months ago
2011
Abstract. In the 2nd Annual FOCS (1961), Chao-Kong Chow proved that every Boolean threshold function is uniquely determined by its degree-0 and degree-1 Fourier coefficients. These...
COLT
1999
Springer
13 years 11 months ago
1999
Springer
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
KDD
2009
ACM
14 years 8 months ago
2009
ACM
In recent years, the blogosphere has experienced a substantial increase in the number of posts published daily, forcing users to cope with information overload. The task of guidin...
ML
2006
ACM
14 years 1 months ago
2006
ACM
Existing ML-like languages guarantee type-safety, ensuring memty and protecting the invariants of abstract types, but only within single executions of single programs. Distributed...
ICIP
2006
IEEE
14 years 9 months ago
2006
IEEE
In this paper, we present a framework for the design of steganographic schemes that can provide provable security by achieving zero Kullback-Leibler divergence between the cover a...