AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement

Shutong Ding, Yimiao Zhou, Ke Hu, Xi Yao, Junchi Yan, Xiaoying Tang, Ye Shi

ICML 2026 · Image generation › Fast diffusion sampling · approach: Guidance for conditional diffusion · 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
add reset operation (ablation)DiOpt · QPSRfeasibility (%): 70.03 -> 81.19Improved
add reset operation (ablation)DiOpt · CQPfeasibility (%): 83.79 -> 87.07Improved
add look-up table of best solutions (ablation)DiOpt · QPSRoptimality gap (%): 112.8 -> 6.69Improved
add look-up table of best solutions (ablation)DiOpt · QPSRaverage constraint violation: 0.120 -> 0.008Improved
add bootstrapped refinement stage on top of supervised diffusion (RectFlow)DiOpt · QPSRfeasibility (%): 0.00 -> 81.87Improved
add bootstrapped refinement stage on top of supervised diffusion (RectFlow)DiOpt · ACOPF118feasibility (%): 0.00 -> 84.33Improved
DiOpt versus DC3 on ACOPF57DiOpt · ACOPF57feasibility (%): 94.00 -> 93.33Hurt
increase diffusion steps T to 100 (ablation)DiOpt · QPSR, CQP, ACOPF, Retargetingoptimality gapImproved
increase T from 5 to 100 (training time) (ablation)DiOpt · QPSRtraining time (hours): 3.09 -> 53.35Hurt
reduce supervised ratio r_s to 0.02 (ablation)DiOpt · QP and QPSR (dim 100)objective performanceHurt
increase training samples K_t (ablation)DiOpt · QPSRobjective vs feasibilityMixed
set noise level eta=0 (no noise injection) (ablation)DiOpt · toy examplesample diversityHurt

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