AI Paper Atlas

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

High Dimensional Structured Superposition Models

Qilong Gu, Arindam Banerjee

NeurIPS 2016 · Learning theory and algorithms › Matrix and tensor methods · approach: High-dimensional estimation theory · 3 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 ambient dimension p (20 to 160) in noiseless MCA recoveryproposed superposition estimator · synthetic noiseless MCA k=2sample complexity for exact recoveryHurt
choose Q with rho=1/sqrt(2) (Q=I) vs rho=0 (Q=-I) vs random Q (ablation)proposed superposition estimator · synthetic noisy MCA k=2, p=1000average L1-type estimation errorImproved
use k-support norm instead of l1 norm for sparse components, increase sparsity s1,s2 from 2 to 3proposed superposition estimator with k-support norm · synthetic MCA with DCT Q, p=100 and 150estimation error sum of componentwise errorsHurt

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