A Temporally Abstracted Viterbi Algorithm
Abstract
Hierarchical problem abstraction, when applicable, may offer exponential reductions in computational complexity. Previous work on coarse-to-fine dynamic programming (CFDP) has demonstrated this possibility using state abstraction to speed up the Viterbi algorithm. In this paper, we show how to apply temporal abstraction to the Viterbi problem. Our algorithm uses bounds derived from analysis of coarse timescales to prune large parts of the state trellis at finer timescales. We demonstrate improvements of several orders of magnitude over the standard Viterbi algorithm, as well as significant speedups over CFDP, for problems whose state variables evolve at widely differing rates.
Cite
Text
Chatterjee and Russell. "A Temporally Abstracted Viterbi Algorithm." Conference on Uncertainty in Artificial Intelligence, 2011.Markdown
[Chatterjee and Russell. "A Temporally Abstracted Viterbi Algorithm." Conference on Uncertainty in Artificial Intelligence, 2011.](https://mlanthology.org/uai/2011/chatterjee2011uai-temporally/)BibTeX
@inproceedings{chatterjee2011uai-temporally,
title = {{A Temporally Abstracted Viterbi Algorithm}},
author = {Chatterjee, Shaunak and Russell, Stuart},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2011},
pages = {96-104},
url = {https://mlanthology.org/uai/2011/chatterjee2011uai-temporally/}
}