AI Paper Atlas

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

An Improved Analysis of Alternating Minimization for Structured Multi-Response Regression

Sheng Chen, Arindam Banerjee

NeurIPS 2018 · 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
Initialize AltMin randomly instead of with OLS, with n >= 40 (ablation)AltMin with HTP theta-step · Synthetic sparse multi-response regression (p=1000, s=20, m=10, a=0.9)normalized L2-errorNo clear effect
Initialize AltMin randomly instead of with OLS, with n < 40 (ablation)AltMin with HTP theta-step · Synthetic sparse multi-response regression (p=1000, s=20, m=10, a=0.9)normalized L2-errorHurt
Use AltMin joint noise-covariance estimation instead of ordinary least squaresOLS estimator · Synthetic sparse multi-response regression (m=10, a=0.9)normalized L2-errorImproved
Increase sample size n from 30 to 60randomly-initialized AltMin · Synthetic data, error vs iterationconvergence speedImproved
Increase noise correlation a from 0.5 to 0.9AltMin · Synthetic data, n=30,40,50,60normalized L2-error: a: 0.5 -> 0.9Improved
Increase noise correlation a so oracle gains more over OLSoracle vs OLS · Synthetic data, n=60e_orc / e_odn ratioImproved
Increase number of responses m from 10 to 18AltMin · Synthetic data, a=0.8, n=30,40,60,80normalized L2-error: m: 10 -> 18No clear effect
Increase number of responses m while comparing AltMin with OLSAltMin · Synthetic data, n=30, a=0.8normalized L2-error vs OLSHurt

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