Decomposable Probability-of-Success Metrics in Algorithmic Search

Tyler Sam, Jake Williams, Abel Tadesse, Huey Sun, George Montañez

2020

Abstract

Prior work in machine learning has used a specific success metric, the expected per-query probability of success, to prove impossibility results within the algorithmic search framework. However, this success metric prevents us from applying these results to specific subfields of machine learning, e.g. transfer learning. We define decomposable metrics as a category of success metrics for search problems which can be expressed as a linear operation on a probability distribution to solve this issue. Using an arbitrary decomposable metric to measure the success of a search, we demonstrate theorems which bound success in various ways, generalizing several existing results in the literature.

Paper Citation

in Harvard Style

Sam T., Williams J., Tadesse A., Sun H. and Montañez G. (2020). Decomposable Probability-of-Success Metrics in Algorithmic Search. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-395-7, pages 785-792. DOI: 10.5220/0009098807850792

in Bibtex Style

@conference{icaart20,
author={Tyler Sam and Jake Williams and Abel Tadesse and Huey Sun and George Montañez},
title={Decomposable Probability-of-Success Metrics in Algorithmic Search},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2020},
pages={785-792},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009098807850792},
isbn={978-989-758-395-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Decomposable Probability-of-Success Metrics in Algorithmic Search
SN - 978-989-758-395-7
AU - Sam T.
AU - Williams J.
AU - Tadesse A.
AU - Sun H.
AU - Montañez G.
PY - 2020
SP - 785
EP - 792
DO - 10.5220/0009098807850792