Universal Prediction of Selected Bits
Abstract
Many learning tasks can be viewed as sequence prediction problems. For example, online classification can be converted to sequence prediction with the sequence being pairs of input/target data and where the goal is to correctly predict the target data given input data and previous input/target pairs. Solomonoff induction is known to solve the general sequence prediction problem, but only if the entire sequence is sampled from a computable distribution. In the case of classification and discriminative learning though, only the targets need be structured (given the inputs). We show that the normalised version of Solomonoff induction can still be used in this case, and more generally that it can detect any recursive sub-pattern (regularity) within an otherwise completely unstructured sequence. It is also shown that the unnormalised version can fail to predict very simple recursive sub-patterns.
Cite
Text
Lattimore et al. "Universal Prediction of Selected Bits." International Conference on Algorithmic Learning Theory, 2011. doi:10.1007/978-3-642-24412-4_22Markdown
[Lattimore et al. "Universal Prediction of Selected Bits." International Conference on Algorithmic Learning Theory, 2011.](https://mlanthology.org/alt/2011/lattimore2011alt-universal/) doi:10.1007/978-3-642-24412-4_22BibTeX
@inproceedings{lattimore2011alt-universal,
title = {{Universal Prediction of Selected Bits}},
author = {Lattimore, Tor and Hutter, Marcus and Gavane, Vaibhav},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {2011},
pages = {262-276},
doi = {10.1007/978-3-642-24412-4_22},
url = {https://mlanthology.org/alt/2011/lattimore2011alt-universal/}
}