AI Paper Atlas

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

Rate-Optimal Subspace Estimation on Random Graphs

Zhixin Zhou, Fan Zhou, Ping Li, Cun-Hui Zhang

NeurIPS 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory · 0 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 soft instead of hard singular value thresholding when the regularization constant cannot be tuned wellSingular value thresholding estimator of M · Simulation, n1=n2=1000, r=3estimation lossImproved
Use hard instead of soft thresholding with a well-chosen regularization constant, measured in operator normSingular value thresholding estimator of M · Simulation, n1=n2=1000, r=3operator norm lossImproved
Use soft instead of hard thresholding, measured in Frobenius normSingular value thresholding estimator of M · Simulation, n1=n2=1000, r=3Frobenius norm lossImproved
Add degree regularization (varying constant c from 0.2 to 1) to hard thresholding (ablation)Algorithm 1 (hard SVT) · Simulation, p=0.01operator and Frobenius lossImproved
Increase graph density p from 0.01 to 0.03 and 0.05Degree regularization effect · Simulation, n1=n2=1000, r=3loss: 0.01, 0.03, 0.05Hurt
Add regularization to soft thresholding (ablation)Algorithm 2 (soft SVT) · Simulation, n1=n2=1000, r=3operator and Frobenius lossNo clear effect
Set regularization constant to 0.8 rather than 0.7 or 0.9Algorithm 2 (soft SVT) · Simulation, p=0.01loss: 0.8 vs 0.7 and 0.9Improved
Use regularization constant above 0.6 for soft thresholdingAlgorithm 2 (soft SVT) · Simulation, p=0.03 and 0.05loss: greater than 0.6No clear effect
Vary regularization constant for subspace estimationAlgorithm 3 (singular space estimation) · Simulation, n1=n2=2000, r=3operator norm lossNo clear effect
Set regularization constant around 0.5Algorithm 3 (singular space estimation) · Simulation, n1=n2=2000, r=3Frobenius norm loss: around 0.5Improved

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