Optimal Ridge Detection using Coverage Risk

Authors: Yen-Chi Chen, Christopher R. Genovese, Shirley Ho, Larry Wasserman

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We apply our method to three simulated datasets and to cosmology data. In all the examples, the proposed method successfully recover the underlying density structure. In all simulations, our selection rule allows the SCMS algorithm to detect the underlying structure of the data.
Researcher Affiliation Academia Yen-Chi Chen Department of Statistics Carnegie Mellon University yenchic@andrew.cmu.edu Christopher R. Genovese Department of Statistics Carnegie Mellon University genovese@stat.cmu.edu Shirley Ho Department of Physics Carnegie Mellon University shirleyh@andrew.cmu.edu Larry Wasserman Department of Statistics Carnegie Mellon University larry@stat.cmu.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We apply our method to three simulated datasets and to cosmology data. We apply the proposed method to several famous datasets including the spiral dataset, the three spirals dataset, and the NIPS dataset. Now we apply our technique to the Sloan Digital Sky Survey, a huge dataset that contains millions of galaxies.
Dataset Splits Yes The second approach is to use data splitting. We randomly split the data into X 11, , X 1m and X 21, , X 2m, assuming n is even and 2m = n. We compute the estimated manifolds by using half of the data, which we denote as b R 1,n and b R 2,n.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types, memory amounts) used for running its experiments.
Software Dependencies No The paper mentions the use of "Subspace Constrained Mean Shift (SCMS) algorithm" and "kernel density estimator (KDE)" but does not specify any software names with version numbers.
Experiment Setup Yes Therefore, the SCMS algorithm requires a preselected parameter h, which acts as the role of smoothing bandwidth in the kernel density estimator. Having estimated the risk, we select h by h = argmin h hn d Risk 1,n. Note that we also remove the ridges whose density is below 0.05 maxx bpn(x) since they behave like random noise.