Reproduce “Robust Persistence Diagrams using Reproducing Kernels” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Siddharth Vishwanath, Kenji Fukumizu, Satoshi Kuriki, Bharath Sriperumbudur
The authors propose robust persistence diagrams by estimating density with a robust kernel density estimator in an RKHS before forming superlevel-set filtrations. Iterative reweighting reduces contributions from discrepant observations; the paper analyzes diagram influence and derives consistency and confidence-band results. In a two-circle simulation, robust diagrams were closer to a clean-sample KDE reference at 20% contamination, but that proxy is not general ground truth.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.