Random Fourier Features via Fast Surrogate Leverage Weighted Sampling

Authors: Fanghui Liu, Xiaolin Huang, Yudong Chen, Jie Yang, Johan Suykens4844-4851

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on several benchmark datasets demonstrate that our algorithm achieves comparable prediction performance and takes less time cost when compared to (Li et al. 2019).
Researcher Affiliation Academia 1Department of Electrical Engineering (ESAT-STADIUS), KU Leuven, Belgium 2Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, China 3Institute of Medical Robotics, Shanghai Jiao Tong University, China 4School of Operations Research and Information Engineering, Cornell University, USA
Pseudocode Yes Algorithm 1: The Surrogate Leverage Weighted RFF Algorithm in KRR
Open Source Code Yes The source code of our implementation can be found in http://www.lfhsgre.org.
Open Datasets Yes These datasets can be downloaded from https://www.csie.ntu.edu.tw/ cjlin/libsvmtools/ datasets/ or the UCI Machine Learning Repository2.
Dataset Splits Yes The regularization parameter λ is tuned via 5-fold inner cross validation over a grid of {0.05, 0.1, 0.5, 1}.
Hardware Specification Yes All experiments are implemented in MATLAB and carried out on a PC with Intel i5-6500 CPU (3.20 GHz) and 16 GB RAM.
Software Dependencies No The paper states 'All experiments are implemented in MATLAB', but it does not specify a version number for MATLAB or any other software libraries used, which is required for reproducibility.
Experiment Setup Yes We choose the popular shift-invariant Gaussian/RBF kernel for experimental validation, i.e., k(x, x ) = exp( x x 2/σ2). Following (Avron et al. 2017), we use a fixed bandwidth σ = 1 in our experiments. The regularization parameter λ is tuned via 5-fold inner cross validation over a grid of {0.05, 0.1, 0.5, 1}.