AI Paper Atlas

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

A Nonconvex Framework for Structured Dynamic Covariance Recovery

Katherine Tsai, Mladen Kolar, Sanmi Koyejo

NeurIPS 2022 · Learning theory and algorithms › Matrix and tensor methods · approach: High-dimensional estimation theory

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 projected-gradient iterative refinement after spectral initialization (ablation)Dynamic covariance estimation · High-dimensional low-rank simulation, 10 training subjectsaverage log-Euclidean distance: 0.43\pm0.01 -> 0.42\pm0.03Improved
add projected-gradient iterative refinement after spectral initialization (ablation)Dynamic covariance estimation · High-dimensional low-rank simulation, 50 training subjectsaverage log-Euclidean distance: 0.39\pm0.01 -> 0.32\pm0.02Improved
add a QR decomposition step (ablation)Proposed model · High-dimensional low-rank simulation, 10 training subjectsaverage log-Euclidean distance: 0.42\pm0.03 -> 0.40\pm0.04No clear effect
add a QR decomposition step (ablation)Proposed model · High-dimensional low-rank simulation, 50 training subjectsaverage log-Euclidean distance: 0.32\pm0.02 -> 0.32\pm0.02No clear effect
use the proposed structured covariance model instead of sliding window shrunk covarianceHCP motor task classification · HCP motor task, 10 training subjectstest classification accuracy: 70.9\pm2.7 -> 61.5\pm7.4Hurt
use the proposed structured covariance model instead of sparse dictionary learningHCP motor task classification · HCP motor task, 10 training subjectstest classification accuracy: 52.6\pm8.3 -> 61.5\pm7.4Improved
use the proposed structured covariance model instead of sparse dictionary learningHCP motor task classification · HCP motor task, 50 training subjectstest classification accuracy: 90.5\pm2.5 -> 90.5\pm2.5No clear effect
increase the model rankProposed model · High-dimensional low-rank simulationaverage log-Euclidean distanceHurt
under-select sparsity level or rankProposed model · Dynamic covariance estimationevaluation scoreHurt
vary the kernel length scale and smoothness coefficientProposed model · Dynamic covariance estimationestimation performanceNo 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