AI Paper Atlas

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

Scalable and Adaptive Trust-Region Learning via Projection Convex Hull

Hongyang Jia, Qingchun Hou, Bojun Du, Xiao Cai, Ning Zhang, Chongqing Kang

ICLR 2026 · Learning theory and algorithms › Matrix and tensor methods · approach: Nonconvex low-rank and sparse optimization

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 PCH instead of CGHCCGHC · PH 15 100trust-region accuracy (%): 57.20 -> 99.95Improved
use PCH instead of PinCHDPinCHD · NLC N 100trust-region accuracy (%): 53.75 -> 99.01Improved
use PCH instead of DeepHullDeepHull · PH 15 100trust-region accuracy (%): 64.39 -> 99.95Improved
use PCH instead of PinCHDPinCHD · PH 15 100number of hyperplanes: 1499 -> 15Improved
use PCH instead of QH on low-dim nonconvex dataQH · NLNC N 2trust-region accuracy (%): 92.15 -> 92.10No clear effect
use PCH instead of CGHCCGHC · Spambasetrust-region accuracy (%): 86.70 -> 94.41Improved
use PCH instead of DeepHullDeepHull · HIVtrust-region accuracy (%): 99.55 -> 99.94Improved
add PCH trust-region filtering at inferenceCART classifier · spambaseclassification accuracy (%): 91.10 -> 93.27Improved
retrain classifier on PCH trust region samplesCART classifier · NLNC N 2classification accuracy (%): 98.30 -> 99.00Improved
add PCH† filtering to MLP constraint learningMLP constraint learner · Constraint learningfeasibility rate (%): 88% to 94%Improved
add PCH† filtering to MLP constraint learningMLP constraint learner · Constraint learningbinary variables: 205 to 35Improved

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