AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Graph Resistance and Learning from Pairwise Comparisons

Julien Hendrickx, Alexander Olshevsky, Venkatesh Saligrama

ICML 2019 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features · 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
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · Lineasymptotic relative-error bound: b^{5/2} n^2 -> b \sqrt{n}Improved
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · Circleasymptotic relative-error bound: b^{5/2} n^2 -> b \sqrt{n}Improved
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · 2D gridasymptotic relative-error bound: b^{5/2} n -> bImproved
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · 3D gridasymptotic relative-error bound: b^{5/2} n^{2/3} -> bImproved
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · Star graphasymptotic relative-error bound: b^{5/2} \sqrt{n} -> bImproved
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · 2 stars joined at centersasymptotic relative-error bound: b^{5/2} n^{1.5} -> bImproved
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · Barbell graphasymptotic relative-error bound: b^{5/2} n^{3.5} -> b \sqrt{n}Improved
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · Geometric random graphasymptotic relative-error bound: b^{5/2} n -> bImproved
Use log-least-squares estimation from edgewise win ratios instead of the earlier eigenvector methodBTL pairwise-comparison learning · Erdos-Renyiasymptotic relative-error bound: b^{5/2} -> bImproved
Increase comparisons per edge kLog-least-squares · Erdos-Renyi graphsrelative estimation errorImproved
Increase expected degree while keeping node count fixedLog-least-squares · Erdos-Renyi graphsaverage relative estimation errorImproved
Increase node count while keeping expected degree fixedLog-least-squares · Erdos-Renyi graphsaverage relative estimation errorNo clear effect

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