mlsanityData to 7 Oct 2026

Accelerating Diffusion-based Combinatorial Optimization Solvers by Progressive Distillation

arXiv 2308.06644 ↗First posted 12 Aug 2023cs.LG cs.AIcited by 4

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Graph-based diffusion models have shown promising results in terms of generating high-quality solutions to NP-complete (NPC) combinatorial optimization (CO) problems. However, those models are often inefficient in inference, due to the iterative evaluation nature of the denoising diffusion process. This paper proposes to use progressive distillation to speed up the inference by taking fewer steps (e.g., forecasting two steps ahead within a single step) during the denoising process. Our experimental results show that the progressively distilled model can perform inference 16 times faster with only 0.019% degradation in performance on the TSP-50 dataset.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 17 of its 22 references that are in the map. First posted on arXiv 12 Aug 2023.

Builds on

17 of 22 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization16 Feb
  2. 2022Scalable Diffusion Models with Transformers19 Dec
  3. 2022On Distillation of Guided Diffusion Models6 Oct
  4. 2022Diffusion models as plug-and-play priors17 Jun
  5. 2020Denoising Diffusion Implicit Models6 Oct
  6. 2020Denoising Diffusion Probabilistic Models19 Jun
  7. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 10

  1. 2016Neural Combinatorial Optimization with Reinforcement Learningcited by 600
  2. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
  3. 2019An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problemcited by 265
  4. 2018Learning to Perform Local Rewriting for Combinatorial Optimizationcited by 183
  5. 2019Learning Improvement Heuristics for Solving Routing Problemscited by 162
  6. 2020Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphscited by 115
  7. 2019Exploratory Combinatorial Optimization with Reinforcement Learningcited by 82
  8. 2022Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxationcited by 32
  9. 2021Pro-KD: Progressive Distillation by Following the Footsteps of the Teachercited by 16
  10. 2021Reversible Action Design for Combinatorial Optimization with Reinforcement Learningcited by 7

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimizationcited by 19
  2. 2024Effective Generation of Feasible Solutions for Integer Programming via Guided Diffusioncited by 8
  3. 2025Bezier Distillationcited by 1
  4. 2025A Denoising Diffusion-Based Evolutionary Algorithm Framework: Application to the Maximum Independent Set Problemcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Parallel Tempering for Diffusion-Based Combinatorial Optimization
  2. 2024DISCO: Efficient Diffusion Solver for Large-Scale Combinatorial Optimization Problems
  3. 2025Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization
  4. 2026Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching
  5. 2025Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation
  6. 2024A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
  7. 2026Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
  8. 2025ReDiF: Reinforced Distillation for Few Step Diffusion