AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Information-Theoretic Compressive Measurement Design

Liming Wang, Minhua Chen, Miguel R. D. Rodrigues, David S. Wilcox, Robert Calderbank, Lawrence Carin

TPAMI 2016 · Optimization › Implicit bias and generalization · approach: Low-rank and single-index recovery

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 ITM with b=0.5 instead of pure signal recovery designpure signal recovery (PSR) · Satellite classification, L=5, m=3Classification accuracy: 0:8400 -> 0:8575Improved
use ITM with b=0.5 instead of pure classification designpure classification (PC) · Satellite signal recovery, L=5, m=3Fractional error: 0:5233 -> 0:4897Improved
ITM b=0.5 versus pure classification design in accuracypure classification (PC) · Satellite classification, L=5, m=3Classification accuracy: 0:8600 -> 0:8575Hurt
ITM b=0.5 versus LDA for classificationLDA · Satellite classification, L=5, m=3Classification accuracy: 0:8535 -> 0:8575Improved
ITM b=0.5 versus LDA for recoveryLDA · Satellite signal recovery, L=5, m=3Fractional error: 0:6876 -> 0:4897Improved
increase number of measurements m from 1 to 2 for ITM b=0.5 (ablation)ITM · Satellite classification, L=5Classification accuracy: 0:4935 -> 0:8265Improved
raise b from 1 to 100 (lower rank) (ablation)ITM · Satellite classification vs rankClassification accuracy: 0.9012 -> 0.6343Hurt
rank-reduce projection matrix after design (ablation)ITM b=10 · Satellite classificationClassification accuracy: 0.8642 -> 0.8622No clear effect
raise b from 50 to 500 on USPS (lower rank) (ablation)ITM · USPS classification vs rankClassification accuracy: 0.9131 -> 0.3416Hurt
rank-reduce projection matrix on USPS (ablation)ITM b=50 · USPS classificationClassification accuracy: 0.9131 -> 0.9119No clear effect
use LDA and IDA instead of ITM for USPS recoveryLDA, IDA · USPS signal recoveryFractional errorHurt
energy constraint L=1 instead of L=5 (ablation)ITM · SatelliteClassification accuracyNo 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