atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist

ICML 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking models from comparisons · 0 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Increase number of alternatives m with fixed dispersion phi in classic Mallows modelClassic Mallows model · Theory (asymptotic, m→∞)normalized expected swap distance g^swap_m(phi)Hurt
Parameterize Mallows by normalized dispersion (norm-phi) instead of classic phi as m growsNormalized Mallows model · Real-world profiles (American Football, Spotify, Tour de France)normalized positionwise distance from IDHelped
Sample profiles from classic Mallows with fixed phi and varying mClassic Mallows model · Plurality score of winner, 100 rankingsPlurality score of Plurality winnerMixed
Use classic Mallows probability of c1 ranked first asymptotically (fixed phi)Classic Mallows model · Theory (asymptotic)P(c1 ranked first)No clear effect
Use normalized Mallows model for probability that c1 is ranked before cmNormalized Mallows model · Theory (asymptotic)P(c1 before cm)No 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