Implementation Issues in the Fourier Transform Algorithm

The Fourier transform of boolean functions has come to play an important role in proving many important learnability results. We aim to demonstrate that the Fourier transform techniques are also a useful and practical algorithm in addition to being a powerful theoretical tool. We describe the more prominent changes we have introduced to the algorithm, ones that were crucial and without which the performance of the algorithm would severely deterio(cid: 173) rate. One of the benefits we present is the confidence level for each prediction which measures the likelihood the prediction is correct.

Authors

• Yishay Mansour School of Computer Science, Tel Aviv University Google Research, Tel Aviv
• Sigal Sahar

Keywords

No keywords are indexed for this paper.