AI Paper Atlas

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

A Note on Sparse Generalized Eigenvalue Problem

YUNFENG CAI, Guanhua Fang, Ping Li

NeurIPS 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse regression with guarantees · 2 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 n from 100 to 6400NC-SGEP · Synthetic |S|=2estimation error: 0.140 -> 0.008Improved
Increase sample size n from 100 to 6400NC-SGEP · Synthetic |S|=8estimation error: 0.277 -> 0.028Improved
Increase support size |S| from 2 to 8NC-SGEP · Synthetic n=1600estimation error: 0.019 -> 0.058Hurt
Unknown support (Est) versus known support (Oracle)NC-SGEP · Synthetic |S|=2, n=100estimation error: 0.056 -> 0.140Hurt
Unknown support versus Oracle at large nNC-SGEP · Synthetic |S|=2, n=6400estimation error: 0.007 -> 0.008No clear effect
Unknown support versus Oracle with small n and large supportNC-SGEP · Synthetic |S|=8, n=100estimation error: 0.173 -> 0.277Hurt
NC-SGEP instead of SDP_L1NC-SGEP · Sparse CCA p=256||x_hat x_hat^T - u1 u1^T||_inf: 0.100 -> 0.084Improved
NC-SGEP instead of SDP_MCPNC-SGEP · Sparse CCA p=256||x_hat x_hat^T - u1 u1^T||_inf: 0.096 -> 0.084Improved
NC-SGEP instead of SDP_L1NC-SGEP · Sparse CCA p=16||x_hat x_hat^T - u1 u1^T||_inf: 0.071 -> 0.074No clear effect
Increase dimension p from 16 to 256NC-SGEP · Sparse CCArecovery of |S|: 93 % -> 49 %Hurt
NC-SGEP versus SDP methods for support recoveryNC-SGEP · Sparse CCArecovery of |S|Improved

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