AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Unfolding-Model-Based Visualization: Theory, Method and Applications

Yunxiao Chen, Zhiliang Ying, Haoran Zhang

JMLR 2021 · Learning theory and algorithms › Sample complexity · approach: Density and property estimation · 3 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
increase sample size J from 200 to 1000MDU · Study Ipartial distance loss (median): 0.0647 -> 0.0134Improved
increase sample size J from 200 to 1000MDU · Study Iconfiguration recovery loss (median): 0.0160 -> 0.0032Improved
fit with extra latent dimension K+=3 instead of true K=2 (ablation)MDU · Study II, J=200partial distance loss (median): 0.0647 -> 0.0758Hurt
fit with extra latent dimension K+=3 instead of true K=2 (ablation)MDU · Study II, J=1000configuration recovery loss (median): 0.0032 -> 0.0345Hurt
fit with extra latent dimension K+=3 instead of true K=2 (ablation)MDU · Study II, J=1000computation time (median): 272.6 -> 2480.8Hurt
use ten random starting pointsMDU optimization · Study Ilikelihood at estimate vs truth: larger than at true parameters for all 100 datasetsImproved
vary link offset delta (0.05, 0.15, 0.2 vs 0.1) (ablation)MDU · MovieLensvisualization: delta 0.1 vs 0.05, 0.15, 0.2No 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