AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Homogeneity Structure Learning in Large-scale Panel Data with Heavy-tailed Errors

Di Xiao, Yuan Ke, Runze Li

JMLR 2021 · Probabilistic and scientific modeling › Molecules and proteins · approach: Statistical analysis of ML practice · 7 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 robust (Huber) covariance estimation instead of sample covariancelatent factor estimation · Covariance estimation, Pareto errorscovariance error (max norm): 6.662 -> 0.297Improved
use robust covariance instead of sample covariancelatent factor estimation · Covariance estimation, t2.1 errorscovariance error (Frobenius): 0.917 -> 0.437Improved
use robust covariance instead of sample covariancelatent factor estimation · Covariance estimation, Normal errorscovariance error (max norm): 0.022 -> 0.022No clear effect
use adaptive Huber instead of median-of-means covariancecovariance estimation · Covariance estimation, Normal errorscovariance error (max norm): 0.027 -> 0.022Improved
compare fast data-driven robustification vs Ahcovariance estimation · Covariance estimation, Pareto errorscovariance error (max norm): 0.298 -> 0.297No clear effect
add robust estimation (vs Homogeneity estimator, OLS-based) (ablation)homogeneity estimator · Coefficient estimation, heavy-tailed errorsRMSEImproved
add homogeneity detection (vs Robust estimator without it) (ablation)robust estimator · Coefficient estimation RMSERMSEImproved
increase signal strength r from 1 to 4homogeneity detection · 5-groups, Pareto errorsadjusted Rand index: 0.9967 -> 0.9997Improved
increase signal strength r from 1 to 4homogeneity detection · 9-groups, Pareto errorsadjusted Rand index: 0.9940 -> 0.9998Improved
make errors serially dependenthomogeneity detection · 5-groups, r=1, Pareto errorsadjusted Rand index: 0.9967 -> 0.9865Hurt
vary robustification parameter tau (ablation)robust covariance and robust regression · Sensitivity (Figure 11)Frobenius error / RMSENo clear effect
learn homogeneity structure with robust estimation instead of OLSPM2.5 prediction · EPA air pollutant data, rolling windowout-of-sample MSEImproved

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