AI Paper Atlas

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

Recognising Multidimensional Euclidean Preferences

Dominik Peters

AAAI 2017 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking models from comparisons · 37 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
recognise preferences using the usual Euclidean ℓ2 metric in fixed dimension d ≥ 2d-Euclidean preference profiles · d-Euclidean preference profiles, fixed d ≥ 2recognition complexity: ∃R-completeHurt
restrict the dimension to oneEuclidean preference recognition · 1-Euclidean preference profilesrecognition complexity: polynomial-timeImproved
allow dichotomous preferences, including uniform-ball approval preferencesd-Euclidean preference recognition · Dichotomous profiles, fixed d ≥ 2recognition complexity: ∃R-completeNo clear effect
replace the Euclidean ℓ2 metric with the ℓ1 metricEuclidean preference recognition · ℓ1-Euclidean preference profiles, d ≥ 1recognition complexity: contained in NPImproved
replace the Euclidean ℓ2 metric with the ℓ∞ metricEuclidean preference recognition · ℓ∞-Euclidean preference profiles, d ≥ 1recognition complexity: contained in NPImproved
use nlsat to test 2- or 3-Euclidean recognition on PrefLib profilesnlsat · PrefLib profiles testedsolver decision within time limit: one hourHurt
seek a finite forbidden-configuration characterisationd-Euclidean domain · d-Euclidean preference profiles, d ≥ 1existence of finite characterisationHurt

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