AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Generalized Rank-Breaking: Computational and Statistical Tradeoffs

Ashish Khetan, Sewoong Oh

JMLR 2018 · Learning theory and algorithms › Matrix and tensor methods · approach: Structured low-rank learning · 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 generalized rank-breaking instead of inconsistent pairwise rank-breakingPlackett-Luce estimation · Simulated PL data, increasing nMSE of weight estimateImproved
increase rank-breaking order M (ablation)Generalized rank-breaking · Simulated PL data (d=256)MSE of weight estimateImproved
increase number of hyper edges l to large values (ablation)Generalized rank-breaking · Simulated PL data (d=512)MSE of weight estimateHurt
increase top-set size m (large r) (ablation)Generalized rank-breaking · Simulated PL dataMSE of weight estimateImproved
increase top-set size m (small r) (ablation)Generalized rank-breaking · Simulated PL dataMSE of weight estimateMixed
increase dynamic range b (ablation)Generalized rank-breaking · Simulated PL dataMSE of weight estimateHurt
use generalized rank-breaking instead of pairwise rank-breakingGeneralized rank-breaking · Sushi datasetMSE of weight estimateImproved
increase top-set size m (ablation)Generalized rank-breaking · Sushi datasetMSE of weight estimateImproved
use generalized rank-breaking instead of pairwise rank-breakingGeneralized rank-breaking · Jester datasetMSE of weight estimateImproved
increase top-set size m with fixed effective samples (ablation)Generalized rank-breaking · Jester datasetMSE of weight estimateHurt
increase sample size n (ablation)Generalized rank-breaking · Jester datasetMSE of weight estimateImproved

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