Offline to Online Conversion
Machine Learning
2014-07-15 v1 Information Theory
math.IT
Statistics Theory
Computation
Statistics Theory
Abstract
We consider the problem of converting offline estimators into an online predictor or estimator with small extra regret. Formally this is the problem of merging a collection of probability measures over strings of length 1,2,3,... into a single probability measure over infinite sequences. We describe various approaches and their pros and cons on various examples. As a side-result we give an elementary non-heuristic purely combinatoric derivation of Turing's famous estimator. Our main technical contribution is to determine the computational complexity of online estimators with good guarantees in general.
Cite
@article{arxiv.1407.3334,
title = {Offline to Online Conversion},
author = {Marcus Hutter},
journal= {arXiv preprint arXiv:1407.3334},
year = {2014}
}
Comments
20 LaTeX pages