539 search results - page 19 / 108 » Learning Monotonic Linear Functions |
ICML
2003
IEEE
14 years 8 months ago
2003
IEEE
We address the problem of learning distance metrics using side-information in the form of groups of "similar" points. We propose to use the RCA algorithm, which is a sim...
ECSQARU
2007
Springer
14 years 1 months ago
2007
Springer
Abstract. The problem of averaging outcomes under several scenarios to form overall objective functions is of considerable importance in decision support under uncertainty. The fuz...
AAAI
1997
13 years 9 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 ...
ESANN
2004
13 years 9 months ago
2004
Several reinforcement-learning techniques have already been applied to the Acrobot control problem, using linear function approximators to estimate the value function. In this pape...
FOCS
2008
IEEE
14 years 2 months ago
2008
IEEE
We introduce several generalizations of classical computer science problems obtained by replacing simpler objective functions with general submodular functions. The new problems i...