AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Estimation and Quantization of Expected Persistence Diagrams

Vincent Divol, Theo Lacombe

ICML 2021 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 0 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
Estimate the expected persistence diagram with the empirical averageEPD estimation · EPD estimation on P^q_{L,M}expected OT_p^p risk: n^{-1/2}Improved
Impose smoothness on the EPDEPD estimation · Smooth EPD modelsminimax OT_p^p risk: n^{-1/2}No clear effect
Add a diagonal cell to the quantization Voronoi partition (ablation)EPD quantization · Torus EPD quantizationdistortion R_{k,∞}Improved
Add a diagonal cell to the quantization Voronoi partition (ablation)EPD quantization · Torus EPD quantizationdistortion R_{k,2}No clear effect
Remove the diagonal cell from the quantization partition (ablation)Online OT_2 quantization · Torus EPD quantizationcodebook qualityHurt
Use the online quantizer with p=2EPD quantization · Torus EPD quantizationdistortion R_{k,2}No clear effect
Use the online quantizer with p=∞EPD quantization · Torus EPD quantizationdistortion R_{k,∞}Improved
Initialize the online quantizer near an optimal codebookOnline OT_2 quantization · EPD quantizationexpected squared codebook error: (\log n)/nImproved
Estimate the empirical EPD from more observed diagramsEmpirical EPD · Synthetic random triangle PDsconvergence rate of OT_p^p: n^{-0.58}Improved

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