|
NeuroCOLT |
Neural Networks and Computational Learning Theory |
|||||||||
|
|
NeuroCOLT Technical Report NC-TR-02-133
We
improve and extend results on a learning model where an algorithm
has to make a sequence of choices based on an evaluation function.
This evaluation function has to be learned on-line from partial information
and is assumed to be linear. The main innovation of this paper is
the introduction and analysis of a new kind of on-line algorithm which
is "adaptively conservative". This algorithm changes its
current hypothesis only if the hypothesis is substantially wrong.
The analysis of this algorithm establishes performance bounds which
depend more directly on the quality of the best off-line approximation
of the evaluation function. This improves and unifies previous results.
|