AI Paper Atlas

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

Inferring Change Points in High-Dimensional Regression via Approximate Message Passing

Gabriel Arpino, Xiaoqi Liu, Julia Gontarek, Ramji Venkataramanan

JMLR 2025 · 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
use AMP with change point prior instead of DP, DPDU, DCDP and CHARCOAL baselinesAMP for change point regression · Linear model with sparse signal priorHausdorff distanceImproved
use AMP instead of DCDP on large signal dimension compressed sensingAMP · Compressed sensing with change points (p=7225)runtime: one hour vs. no output within 2.5 hoursImproved
run AMP with a mismatched sparsity level of 0.9 for the sparse difference prior (ablation)AMP · Linear model with sparse difference signal priorHausdorff distanceNo clear effect
assume exactly 3 signals instead of up to L=3 or 4 for AMP vs binary segmentation (ablation)AMP vs binary segmentation · Sparse logistic regression with change pointsHausdorff distance and runtimeImproved
increase sampling ratio delta (ablation)AMP posterior · Linear, logistic, ReLU change point modelsposterior concentrationImproved
compare AMP estimated number of change points with state evolution theoryAMP · Logistic and ReLU, single change pointestimated number of change points: 1.10 vs 1.10 (ReLU sigma=0.50, delta=0.75)No 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