loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Julius Lauw ; Dominique Macias ; Akshay Trikha ; Julia Vendemiatti and George D. Montañez

Affiliation: AMISTAD Lab, Department of Computer Science, Harvey Mudd College, Claremont, CA 91711, U.S.A.

Keyword(s): Machine Learning, Algorithmic Search, Inductive Bias, Entropic Expressivity.

Abstract: Learning algorithms need bias to generalize and perform better than random guessing. We examine the flexibility (expressivity) of biased algorithms. An expressive algorithm can adapt to changing training data, altering its outcome based on changes in its input. We measure expressivity by using an information-theoretic notion of entropy on algorithm outcome distributions, demonstrating a trade-off between bias and expressivity. To the degree an algorithm is biased is the degree to which it can outperform uniform random sampling, but is also the degree to which is becomes inflexible. We derive bounds relating bias to expressivity, proving the necessary trade-offs inherent in trying to create strongly performing yet flexible algorithms.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 52.54.103.76

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Lauw, J.; Macias, D.; Trikha, A.; Vendemiatti, J. and Montañez, G. (2020). The Bias-Expressivity Trade-off. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-395-7; ISSN 2184-433X, SciTePress, pages 141-150. DOI: 10.5220/0008959201410150

@conference{icaart20,
author={Julius Lauw. and Dominique Macias. and Akshay Trikha. and Julia Vendemiatti. and George D. Montañez.},
title={The Bias-Expressivity Trade-off},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2020},
pages={141-150},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008959201410150},
isbn={978-989-758-395-7},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - The Bias-Expressivity Trade-off
SN - 978-989-758-395-7
IS - 2184-433X
AU - Lauw, J.
AU - Macias, D.
AU - Trikha, A.
AU - Vendemiatti, J.
AU - Montañez, G.
PY - 2020
SP - 141
EP - 150
DO - 10.5220/0008959201410150
PB - SciTePress