AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Neural Compression of Long ADMM Trajectory for Multiparametric Quadratic Program

Liang Wu, Bo Yang, Xu Yang, Honghui Zheng, Yilin Mo, Jan Drgona

NeurIPS 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervision in supervised pipelines · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes TQPNet, a self-supervised neural compression framework that compresses long ADMM optimization trajectories for multiparametric quadratic programs into a compact neural warm start followed by a few ADMM iterations.

Problem

Solving large-scale multiparametric quadratic programs (mpQPs) in real time requires thousands of iterative ADMM updates, a computational bottleneck for model predictive control and learning-enabled systems.

Approach

Instead of predicting only a solution, a neural network is trained self-supervised to compress an entire long ADMM trajectory into a compact warm start, after which only a few ADMM iterations are run to refine it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add MLP(ReLU) learned warm start before ADMM(ReLU) refinement (ablation)low-dim ADMM(ReLU) · random mpQP n=100, m=200iterations to residual 1e-7: 4729 -> 2778Improved
add 50 ADMM(ReLU) refinement layers after the MLP instead of MLP only (ablation)TQPNet · random mpQP n=100, m=200wall-clock to residual 1e-7: 7.777 ms -> 6.034 msImproved
add only 1 to 5 ADMM(ReLU) refinement layers after the MLP (ablation)TQPNet · random mpQP n=100, m=200wall-clock to residual 1e-7: 7.777 ms -> 8.032 ms (1 layer), 7.751 ms (5 layers)No clear effect
use low-dimensional ADMM-ReLU instead of full-dimensional ADMMADMM for QP · n=100, m=200 random mpQPconvergence to 1e-7: full-dim >10^4 iterations -> 4729Improved
increase unrolling depth K_train from 10 to 25 (ablation)TQPNet training · random mpQP n=100, m=200median test rel error (K_eval=10): 5.8e-01 -> 5.7e-02Improved
increase unrolling depth K_train beyond 25 (to 50) (ablation)TQPNet training · random mpQP n=100, m=200median test rel error (K_eval=10): 5.7e-02 -> 5.6e-02No clear effect
increase unrolling depth K_train from 10 to 50 on small problem (ablation)TQPNet training · random mpQP n=10, m=20median test rel error (K_eval=10): 5.3e-03 -> 3.6e-03 (K=25) -> 1.4e-02 (K=50)Mixed
use self-supervised KKT-residual training instead of label-supervised OSQP regression (TQPNet vs LQPNet) (ablation)MLP(ReLU) warm start · in-distribution n=100, m=200median relative error: 1.5e-02 -> 5.8e-02Hurt
use self-supervised KKT-residual training instead of label-supervised under distribution shift (ablation)MLP(ReLU) warm start · OOD p in U[-3,3]TQP-LQP error gap: 3.9x -> 1.8x gapImproved
use learned warm start instead of cold-start ADMM(ReLU) (K=50) (ablation)MPC closed loop · random MPC scalestracking performanceImproved
use TQPNet instead of OSQP as problem size growsMPC QP solving · random MPC, n+m from 60 to 2800online latency: OSQP 0.03 ms -> 13.06 ms vs TQPNet 1.31 ms -> 1.88 msMixed
use label-free TQPNet training instead of OSQP-labelled LQPNet trainingoffline training · random MPC n+m=2800offline time: 590 s -> 334 sImproved

Experimental setup

Builds on: ADMM

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