mlsanityData to 14 Oct 2026

Constraint-Guided Prediction Refinement via Deterministic Diffusion Trajectories

arXiv 2506.12911 ↗First posted 15 Jun 2025cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Many real-world machine learning tasks require outputs that satisfy hard constraints, such as physical conservation laws, structured dependencies in graphs, or column-level relationships in tabular data. Existing approaches rely either on domain-specific architectures and losses or on strong assumptions on the constraint space, restricting their applicability to linear or convex constraints. We propose a general-purpose framework for constraint-aware refinement that leverages denoising diffusion implicit models (DDIMs). Starting from a coarse prediction, our method iteratively refines it through a deterministic diffusion trajectory guided by a learned prior and augmented by constraint gradient corrections. The approach accommodates a wide class of non-convex and nonlinear equality constraints and can be applied post hoc to any base model. We demonstrate the method in two representative domains: constrained adversarial attack generation on tabular data with column-level dependencies and in AC power flow prediction under Kirchhoff's laws. Across both settings, our diffusion-guided refinement improves both constraint satisfaction and performance while remaining lightweight and model-agnostic.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 15 Jun 2025.

Builds on

23 of 35 references.

References · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2016Adversarial Machine Learning at Scalecited by 936
  6. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 599
  7. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 508
  8. 2019Differentiable Convex Optimization Layerscited by 465
  9. 2018Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimizationcited by 227
  10. 2021DC3: A learning method for optimization with hard constraintscited by 184
  11. 2023Manifold Preserving Guided Diffusioncited by 157
  12. 2022Score-Based Generative Models Detect Manifoldscited by 122
11 more
  1. 2024Constrained Synthesis with Projected Diffusion Modelscited by 89
  2. 2019Learning Optimal Solutions for Extremely Fast AC Optimal Power Flowcited by 77
  3. 2023Diffusion Models for Constrained Domainscited by 63
  4. 2024How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Datacited by 29
  5. 2023Metropolis Sampling for Constrained Diffusion Modelscited by 28
  6. 2021A Unified Framework for Adversarial Attack and Defense in Constrained Feature Spacecited by 22
  7. 2025Training-Free Constrained Generation With Stable Diffusion Modelscited by 20
  8. 2020PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Controlcited by 13
  9. 2024Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Datacited by 11
  10. 2024TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-casescited by 10
  11. 2024Constrained Diffusion with Trust Samplingcited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
  2. 2026From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation
  3. 2025Softly Constrained Denoisers for Diffusion Models Applied to Partial Differential Equations
  4. 2024Constrained Diffusion Models via Dual Training
  5. 2026Integration Matters: Rollout-Based Training for Constrained Diffusion Models
  6. 2024Constraint-Aware Diffusion Models for Trajectory Optimization
  7. 2026DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
  8. 2025Constrained Diffusion Models for Synthesizing Representative Power Flow Datasets