AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Non-Asymptotic Guarantees for Robust Statistical Learning under Infinite Variance Assumption

Lihu Xu, Fang Yao, Qiuran Yao, Huiming Zhang

JMLR 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: High-dimensional estimation theory · 12 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
add log-truncation to DNN LAD under Gaussian pixel noise (20%) (ablation)DNN LAD · MNISTaccuracy (%): 75.71 -> 86.85Improved
add log-truncation to DNN LAD under Uniform pixel noise (80%) (ablation)DNN LAD · MNISTaccuracy (%): 91.65 -> 93.45Improved
add log-truncation to DNN LAD under Pareto pixel noise (80%) (ablation)DNN LAD · MNISTaccuracy (%): 60.96 -> 65.12Improved
add log-truncation to standard LAD regression (ablation)l2-regularized LAD · Boston housingMAE: 6.4843 -> 6.2448Improved
add log-truncation to deep LAD regression (ablation)deep LAD · Boston housingMAE: 6.3186 -> 6.0628Improved
add high-order log-truncation to DNN logistic regression (ablation)DNN logistic regression · Synthetic (d=100, n=1000, Pareto tau=4.01)accuracy (%): 80.13 -> 93.36Improved
add high-order log-truncation to elastic-net logistic regression (ablation)logistic regression · Synthetic (d=100, n=200, Pareto tau=1.60, varsigma=0)l2-estimation error: 3.5344 -> 2.9463Improved
use high-order log-truncation instead of Cauchy 1-order truncation (ablation)log-truncated logistic regression · Synthetic (d=200, n=500, Uniform noise pi=0.3, varsigma=0)l2-estimation error: 4.9339 -> 4.3418Improved
use high-order log-truncation instead of Cauchy truncation (ablation)log-truncated logistic regression · Synthetic (d=100, n=200, Pareto tau=1.60, varsigma=0)l2-estimation error: 3.1587 -> 2.9463Improved
vary truncation index beta from 1.1 to 2.0 (best at 1.8) (ablation)truncated deep LAD · Boston housingMAE: 6.2822 -> 6.0628Mixed

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