---
title: "Search Techniques for Fourier-Based Learning"
authors:
  - "Adam Drake"
  - "Dan Ventura"
doi: ""
url: "https://ijcai.org/proceedings/2009/176"
pdf: "https://ijcai.org/proceedings/2009/0176.pdf"
venue: "Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence"
year: 2009
pages: "1040-1044"
track: ""
keywords:
---

# Search Techniques for Fourier-Based Learning

Adam Drake, Dan Ventura

*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