AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Robust Persistence Diagrams using Reproducing Kernels

Siddharth Vishwanath, Kenji Fukumizu, Satoshi Kuriki, Bharath K. Sriperumbudur

NeurIPS 2020 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace KDE filtration with robust KDE filtrationpersistence diagram · Two circles with outliers, noise 20-40%bottleneck distance to clean diagramImproved
increase outlier noise level from 20% to 40%robust vs KDE persistence diagram · Two circles with outliersbottleneck distance advantageImproved
use robust KDE instead of KDE as filterpersistence diagram · Runtime, torus n=1000, resolution 0.10runtime: 1.8s -> 3.5sNo clear effect
use robust KDE instead of KDE as filterpersistence diagram · Runtime, torus n=1000, resolution 0.04runtime: 75.5s -> 76.7sNo clear effect
use robust diagram Dgm(f) with W1 instead of persistence image of distance function with L1spectral clustering · Six-class 3D shapes, H0Rand index: 78.53% -> 95.30%Improved
use robust diagram with W1 instead of persistence image with L1spectral clustering · Six-class 3D shapes, H1Rand index: 81.89% -> 91.43%Improved
use robust diagram with W1 instead of persistence image with L1spectral clustering · Six-class 3D shapes, H2Rand index: 80.09% -> 86.33%Improved
use robust diagram with W2 instead of persistence image with L2spectral clustering · Six-class 3D shapes, H2Rand index: 77.12% -> 73.91%Hurt
use robust diagram with W1 instead of persistence image with L1 on combined max distancespectral clustering · Six-class 3D shapes, maxRand index: 82.43% -> 95.72%Improved
use robust KDE persistence images instead of KDE or DTMlinear SVM on persistence images · MPEG7 3-class and 5-class with 15% noiseclassification errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy