CUED Publications database

The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings

Choromanski, K and Rowland, M and Weller, A (2017) The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings. In: Neural Information Processing Systems 2017, 2017-12-4 to 2017-12-9, Long Beach Convention Center, Long Beach pp. 219-228..

Full text not available from this repository.


We examine a class of embeddings based on structured random matrices with orthogonal rows which can be applied in many machine learning applications including dimensionality reduction and kernel approximation. For both the Johnson-Lindenstrauss transform and the angular kernel, we show that we can select matrices yielding guaranteed improved performance in accuracy and/or speed compared to earlier methods. We introduce matrices with complex entries which give significant further accuracy improvement. We provide geometric and Markov chain-based perspectives to help understand the benefits, and empirical results which suggest that the approach is helpful in a wider range of applications.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: stat.ML stat.ML stat.CO
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 15 Nov 2017 20:14
Last Modified: 30 Mar 2021 07:26