SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm

Authors: Yi Hao, Ayush Jain, Alon Orlitsky, Vaishakh Ravindrakumar

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

Reproducibility Variable Result LLM Response
Research Type Experimental In experiments, SURF outperforms state-of-the art algorithms. and We conclude in Section 5 with a detailed comparison of SURF and ADLS, and show experimental results that confirm the theory and show that SURF performs well for a variety of distributions. and Our experiments show that SURF is more adaptive than ADLS, and perform additional experiments on both synthetic and real datasets.
Researcher Affiliation Academia Yi Hao, Ayush Jain, Alon Orlitsky, Vaishakh Ravindrakumar Dept. of Electrical and Computer Engineering University of California, San Diego {yih179, ayjain, aorlitsky, varavind}@eng.ucsd.edu
Pseudocode No The paper describes the routines INT, MERGE, and COMP in text, but it does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described, nor does it state that the code is available.
Open Datasets Yes Finally, we ran SURF on real data sets consisting of salaries from the 1994 US census and electric signals from the sensorless drive diagnosis dataset [8], that have been used to evaluate classification algorithms [10, 4, 14].
Dataset Splits No The paper mentions evaluating on 'a test set with one-fourth the number of samples' but does not provide specific training, validation, or the full partitioning details needed for reproduction.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions the use of 'MATLAB R' for a function, but it does not specify version numbers for MATLAB or any other key software dependencies.
Experiment Setup Yes SURF is run with α = 0.25 and the errors are averaged over 10 runs. and Evaluation of the estimate output by SURF with degrees d = 1, 2, 3, α = 0.25