22 search results - page 1 / 5 » Worst-Case Absolute Loss Bounds for Linear Learning Algorith... |
AAAI
1997
13 years 6 months ago
1997
The absolute loss is the absolute difference between the desired and predicted outcome. I demonstrateworst-case upper bounds on the absolute loss for the perceptron algorithm and ...
AI
1998
Springer
13 years 4 months ago
1998
Springer
The absolute loss is the absolute difference between the desired and predicted outcome. This paper demonstrates worst-case upper bounds on the absolute loss for the Perceptron le...
NIPS
2004
13 years 6 months ago
2004
We provide a worst-case analysis of selective sampling algorithms for learning linear threshold functions. The algorithms considered in this paper are Perceptron-like algorithms, ...
JMLR
2006
13 years 4 months ago
2006
A selective sampling algorithm is a learning algorithm for classification that, based on the past observed data, decides whether to ask the label of each new instance to be classi...
NIPS
2004
13 years 6 months ago
2004
We present a competitive analysis of Bayesian learning algorithms in the online learning setting and show that many simple Bayesian algorithms (such as Gaussian linear regression ...