BM 20160628

Tue Jun 28 09:52:21 CDT 2016 957df6f2b8b9afc9b83d06ddfb3f09e69c359c67

Noisy Data

Tree structure: from simple, to complex

Data on linear edge

☛

Data on simple branch

☛

Data on a “complex” tree

☛

Noise

Three types of noise are simulated:

• Noisy samples, \(X_{ij} = X_{ij} + N(0, \sigma)\)
• Noisy features, \(X = [X, E], E\sim MVN(0, \sigma I)\)
• Combination of the two above

Implementation

All in one DSC script:

dsc exec benchmark.dsc -j8 -s "((SimTree * PlotTree) * SimBM, LinearBM) * (SklearnDR * PlotPY, RDR[1] * PlotR[1], (RDR[2], RDR[3]) * PlotR[2], (RDR[4], RDR[5], RDR[6]) * PlotR[3], RDR[7] * PlotR[4], (RDR[8], RDR[9]) * PlotR[5])"

It takes 3352 seconds to run this benchmark.

Result

Written into this one HTML page.