22 search results - page 4 / 5 » Worst-Case Absolute Loss Bounds for Linear Learning Algorith... |
NIPS
2004
13 years 7 months ago
2004
Prediction suffix trees (PST) provide a popular and effective tool for tasks such as compression, classification, and language modeling. In this paper we take a decision theoretic...
COLT
1999
Springer
13 years 10 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...
CORR
2011
Springer
13 years 1 months ago
2011
Springer
Valiant’s (2007) model of evolvability models the evolutionary process of acquiring useful functionality as a restricted form of learning from random examples. Linear threshold ...
VLDB
2006
ACM
14 years 6 months ago
2006
ACM
We focus on the problem of efficient learning of dependency trees. Once grown, they can be used as a special case of a Bayesian network, for PDF approximation, and for many other u...
ICML
2010
IEEE
13 years 4 months ago
2010
IEEE
Online learning algorithms have recently risen to prominence due to their strong theoretical guarantees and an increasing number of practical applications for large-scale data ana...