Search Techniques for Fourier-Based Learning

Drake, Adam; Ventura, Dan

Search Techniques for Fourier-Based Learning

Download BibTeX Cite

Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence. Pages 1040-1044.

Abstract

Fourier-based learning algorithms rely on being able to efficiently find the large coefficients of a function's spectral representation. In this paper, we introduce and analyze techniques for finding large coefficients. We show how a previously introduced search technique can be generalized from the Boolean case to the real-valued case, and we apply it in branch-and-bound and beam search algorithms that have significant advantages over the best-first algorithm in which the technique was originally introduced.Adam Drake, Dan Ventura

Adam Drake, and Dan Ventura. 2009. Search Techniques for Fourier-Based Learning. In Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09. IJCAI, 1040–1044. https://ijcai.org/proceedings/2009/176

@inproceedings{ijcai2009p176,
  title     = {Search Techniques for Fourier-Based Learning},
  author    = {Drake, Adam and Ventura, Dan},
  booktitle = {Proceedings of the Twenty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-09}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Hiroaki Kitano},
  pages     = {1040--1044},
  year      = {2009},
  url       = {https://ijcai.org/proceedings/2009/176},
}

TY  - CPAPER
TI  - Search Techniques for Fourier-Based Learning
AU  - Drake, Adam
AU  - Ventura, Dan
T2  - Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2009
SP  - 1040
EP  - 1044
UR  - https://ijcai.org/proceedings/2009/176
ER  -