AI Paper Atlas

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

Hierarchical Multi-Stage Recovery Framework for Kronecker Compressed Sensing

Yanbin He, Geethu Joseph

ICLR 2026 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval

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 multi-stage recovery (MSOMP) instead of KroOMPstandard-sparse recovery · Standard sparsity runtimeruntime: 130.5405 -> 0.4256 s at 3 dBImproved
use MSHTP instead of HiHTPhierarchical-sparse recovery · Hierarchical sparsity runtimeruntime: 0.6512 -> 0.0379 s at 3 dBImproved
use MSSBL instead of AM-/SVD-KroSBLKronecker-supported recovery · Kronecker-supported runtimeruntime: 37.1233 -> 0.0728 s at 3 dBImproved
use MSSBL instead of KroOMPstandard-sparse recovery · Standard sparsity NSENSEImproved
use MSHTP/MSIHT instead of HiHTP/HTP/IHThierarchical-sparse recovery · Hierarchical sparsity NSENSENo clear effect
use MSHTP/MSOMP instead of HiHTP/HiIHTchannel estimation · Massive MIMO channel estimation NSENSEMixed
use MSHTP instead of HiHTPchannel estimation · Massive MIMO channel estimation runtimeruntime: 0.0738 -> 0.0195 s at L=5Improved
use MSIHT instead of MSHTPmulti-stage recovery · Hierarchical sparsity, scaling with dimensionNSEHurt

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