AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Distributed Inference for Linear Support Vector Machine

Xiaozhou Wang, Zhuoyi Yang, Xi Chen, Weidong Liu

JMLR 2019 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 54 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 number of aggregation rounds q from 2 to 10 (ablation)MDL · Simulated SVM n=1e6, p=50, m=1000L2 error (x1e-2): 3.223 -> 0.293Improved
increase number of aggregation rounds q from 2 to 10 (ablation)MDL · Simulated SVM n=1e6, p=500, m=6250L2 error (x1e-2): 3.502 -> 0.320Improved
add more rounds beyond q=4 (ablation)MDL · Simulated SVM n=1e6, p=100, m=2000L2 error (x1e-2): 0.372 -> 0.338No clear effect
use MDL multi-round refinement instead of naive divide-and-conquer averagingMDL · Simulated SVM n=1e4, p=4, m=100bias^2 (x1e-4): 59.329 -> 0.004Improved
use MDL instead of Naive-DC at large batch sizeMDL · Simulated SVM n=1e5, p=20, m=5000bias^2 (x1e-4): 0.041 -> 0.000Mixed
increase total sample size n for Naive-DC (ablation)Naive-DC · Simulated SVM m=100, p=4bias^2 (x1e-4): 58.377 -> 60.540No clear effect
increase total sample size n for MDL (ablation)MDL · Simulated SVM m=100, p=4bias^2 (x1e-4): 1.782 -> 0.000Improved
increase total sample size n for MDL (ablation)MDL · Simulated SVM m=100, p=4variance (x1e-4): 55.412 -> 1.611Improved
shrink machine capacity m for Naive-DC (ablation)Naive-DC · Simulated SVM n=1e4, p=4bias^2 (x1e-4): 0.304 -> 59.329Hurt
vary bandwidth constant C0 in {0.5, 1, 2, 5, 10} (ablation)MDL · Simulated SVML2 errorNo 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