Random Fourier Features
Random Fourier Features is a kernel approximation method that maps input data into a randomized low-dimensional Euclidean space by sampling from the Fourier transform of a shift-invariant kernel, thereby enabling scalable kernel learning through explicit feature representations.
112
Publications
3.9K
Citations
314
Authors
153
Institutions
Publications per year
2017–2026
85
Variants
Rff
Parents
112
Nyström Method vs Random Fourier Features: A Theoretical and Empirical Comparison
Tianbao Yang, Yu-Feng Li, Mehrdad Mahdavi et al. · 2012 · 218 citations
Felix X. Yu, Ananda Theertha Suresh, Krzysztof Choromański et al. · arXiv (Cornell University) · 2016 · 104 citations · Full text
1–5 of 112
314
7
h-index
6
h-index
6
h-index
5
h-index
5
h-index
1–5 of 314
153
Southwest University
Chongqing, China
6 h-index
21 publications
840 citations
Indian Institute of Technology Indore
Indore, India
6 h-index
10 publications
239 citations

École de Technologie Supérieure
Montreal, Canada
6 h-index
7 publications
165 citations
Norwegian University of Science and Technology
Trondheim, Norway
5 h-index
11 publications
226 citations
Massachusetts Institute of Technology
Cambridge, United States
5 h-index
7 publications
353 citations
Google (United States)
Mountain View, United States
4 h-index
10 publications
587 citations
Université du Québec à Montréal
Montreal, Canada
4 h-index
6 publications
135 citations
University of Oxford
Oxford, United Kingdom
4 h-index
9 publications
283 citations
1–8 of 153
Repository · 26 publications · 744 citations
16
h-index
5 publications · 201 citations
5
h-index
Conference · 4 publications · 114 citations
4
h-index
3 publications · 55 citations
3
h-index
Conference · 3 publications · 48 citations
3
h-index
1–5