AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

T-SKM-Net: Trainable Neural Network Framework for Linear Constraint Satisfaction via Sampling Kaczmarz-Motzkin Method

Haoyu Zhu, Yao Zhang, Jiashen Ren, Qingchun Hou

AAAI 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Semidefinite relaxations for verification · 1 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 T-SKM-Net instead of Gurobi for L2 projection at large dimensionT-SKM-Net · L2 projection dim 10000time (s): 103.6 s -> 22.82 sImproved
use T-SKM-Net instead of OptNet at 130 inequalitiesT-SKM-Net · Constrained QPtime (ms): 450.6 ms -> 1.0 ms with similar objective (-10.25 vs -10.23)Improved
use T-SKM-Net instead of DC3 at 150 inequalitiesT-SKM-Net · Constrained QPobjective value: objective -9.06 -> -10.24, ineq violation 0.006 -> 0.000Improved
add T-SKM-Net layer to NN (post-processing)NN · Constrained QPmax equality violation: equality violation 0.350 -> 0.000Improved
use T-SKM-Net instead of pandapowerT-SKM-Net · DCOPF IEEE 118-bustime (ms): 141.08 ms -> 4.27 msImproved
use T-SKM-Net instead of DC3T-SKM-Net · DCOPF IEEE 118-bustime (ms): 52.15 ms -> 4.27 ms; DC3 ineq violation 4e-4Improved
joint training instead of post-processing (ablation)T-SKM-Net · S&P 500 portfolio allocationSharpe ratio: Sharpe 2.93 -> 3.02Improved
joint training instead of post-processing (ablation)T-SKM-Net · DCOPF IEEE 118-busoptimality gap / time: gap 1.0e-4 -> 7.0e-5; time 4.27 -> 5.64 msMixed
add MSE punishment to upstream output in joint training (Train-p) (ablation)T-SKM-Net · DCOPF IEEE 118-busoptimality gap (%): gap 7.0e-5 -> 5.4e-5Improved
use T-SKM-Net instead of GLinSATT-SKM-Net · S&P 500 portfolio allocationSharpe ratio: Sharpe 2.28 -> 3.02Improved

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