AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Near-optimal Linear Predictive Clustering in Non-separable Spaces via MIP and QPBO Reductions

Jiazhou Liang, Hassan Khurram, Scott Sanner

AAAI 2026 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 0 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
use LPC-NS-MIP instead of Greedy on real datasetsGreedy · UCI datasets (10)SSE: e.g. 17.1278 -> 12.4745 (Stock Portfolio)Improved
use LPC-NS-QPBO instead of Greedy on real datasetsGreedy · Heart Failure Prediction (519)SSE: 25.0644 -> 4.733 x 10^-30Improved
use LPC-NS-MIP instead of Greedy on Solar FlareGreedy · Solar Flare (89)SSE: 8.3014 -> 11.0511Hurt
use LPC-NS-QPBO instead of LPC-NS-MIP on ServoLPC-NS-MIP · Servo (87)SSE: 2.5305 -> 12.4865Hurt
use LPC-NS-QPBO instead of LPC-NS-MIP on Parkinsons TelemonitoringLPC-NS-MIP · Parkinsons Telemonitoring (189)SSE: 146.9704 -> 135.3372Improved
use w* approximation on non-separable featuresglobal MIP · Synthetic 2-cluster non-separableobjective deviation from optimum: 0.0208Improved
use K-Means+Ridge CLR on non-separable instead of separable featuresCLR · Synthetic 2-clusterobjective deviation from optimum: 0.5996 -> 72.2481Hurt
use LPC-NS-QPBO instead of GlobalOpt for large samplesGlobalOpt · Synthetic K=2scalability (samples within 2 hours): 200 -> 2000Improved
use LPC-NS-QPBO with K=3 instead of K=2LPC-NS-QPBO · Syntheticdeviation from GlobalOptHurt
use Gurobi MIP solver instead of SCIP PBO solver for QPBO (ablation)LPC-NS-QPBO · Synthetic K=2, D=1runtime scalabilityImproved
increase feature dimensionalityGreedy · Syntheticobjective deviationHurt

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