Mixture of Vector Experts
Abstract
We describe and analyze an algorithm for predicting a sequence of n -dimensional binary vectors based on a set of experts making vector predictions in [0,1]^ n . We measure the loss of individual predictions by the 2-norm between the actual outcome vector and the prediction. The loss of an expert is then the sum of the losses experienced on individual trials. We obtain bounds for the loss of our expert algorithm in terms of the loss of the best expert analogous to the well-known results for scalar experts making real-valued predictions of a binary outcome.
Cite
Text
Henderson et al. "Mixture of Vector Experts." International Conference on Algorithmic Learning Theory, 2005. doi:10.1007/11564089_30Markdown
[Henderson et al. "Mixture of Vector Experts." International Conference on Algorithmic Learning Theory, 2005.](https://mlanthology.org/alt/2005/henderson2005alt-mixture/) doi:10.1007/11564089_30BibTeX
@inproceedings{henderson2005alt-mixture,
title = {{Mixture of Vector Experts}},
author = {Henderson, Matthew and Shawe-Taylor, John and Zerovnik, Janez},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {2005},
pages = {386-398},
doi = {10.1007/11564089_30},
url = {https://mlanthology.org/alt/2005/henderson2005alt-mixture/}
}