AI Paper Atlas

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

Ultrahyperbolic Representation Learning

Marc Law, Jos Stam

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 8 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 ultrahyperbolic Q^{3,1} instead of Euclidean R^4graph embedding · Zachary's karate clubrank of first leader: 5.4 -> 1.2Improved
use ultrahyperbolic Q^{3,1} instead of hyperbolic Q^{4,0}graph embedding · Zachary's karate clubrank of first leader: 2.8 -> 1.2Improved
use ultrahyperbolic Q^{3,1} instead of spherical Q^{0,4}graph embedding · Zachary's karate clubrank of second leader: 4.0 -> 2.4Improved
use ultrahyperbolic Q^{3,1} instead of hyperbolic Q^{4,0}graph embedding · Zachary's karate clubtop 5 Spearman's rho: 0.20 -> 0.76Improved
use ultrahyperbolic Q^{2,2} instead of hyperbolic Q^{4,0}graph embedding · Zachary's karate clubtop 10 Spearman's rho: 0.38 -> 0.79Improved
increase time dimensions to Q^{1,3} from Q^{3,1} (ablation)graph embedding · Zachary's karate clubtop 5 Spearman's rho: 0.76 -> 0.36Hurt
use Euclidean norm proxy instead of sum of distances for hyperbolic importance (ablation)hyperbolic embedding · Zachary's karate clubrank of first leader: 2.8 -> 8.6Hurt
use Euclidean norm proxy instead of sum of distances for hyperbolic importance (ablation)hyperbolic embedding · Zachary's karate clubrank of second leader: 4.2 -> 18.6Hurt
use pseudo-Riemannian optimizer instead of Euclidean-gradient mapping optimizer in low dimensions Q^{4,1}, Q^{4,2} (ablation)ultrahyperbolic optimization · Zachary's karate clubsatisfaction of all distance constraintsImproved
use -Df(x) instead of the projected direction -chi as search direction (ablation)pseudo-Riemannian optimizer · Zachary's karate clubconvergenceHurt
use Euclidean-gradient mapping optimizer instead of pseudo-Riemannian optimizer (ablation)ultrahyperbolic optimization · Zachary's karate clubtraining speed: 10% fasterMixed

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