mlsanityData to 14 Oct 2026

Diffusion Models for Black-Box Optimization

arXiv 2306.07180 ↗First posted 12 Jun 2023cs.LGcited by 76

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The goal of offline black-box optimization (BBO) is to optimize an expensive black-box function using a fixed dataset of function evaluations. Prior works consider forward approaches that learn surrogates to the black-box function and inverse approaches that directly map function values to corresponding points in the input domain of the black-box function. These approaches are limited by the quality of the offline dataset and the difficulty in learning one-to-many mappings in high dimensions, respectively. We propose Denoising Diffusion Optimization Models (DDOM), a new inverse approach for offline black-box optimization based on diffusion models. Given an offline dataset, DDOM learns a conditional generative model over the domain of the black-box function conditioned on the function values. We investigate several design choices in DDOM, such as re-weighting the dataset to focus on high function values and the use of classifier-free guidance at test-time to enable generalization to function values that can even exceed the dataset maxima. Empirically, we conduct experiments on the Design-Bench benchmark and show that DDOM achieves results competitive with state-of-the-art baselines.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 39 of its 50 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

39 of 50 references.

Closest ancestors · 10

Same direction, newest first

  1. 2022Blurring Diffusion Models12 Sep
  2. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise19 Aug
  3. 2022Classifier-Free Diffusion Guidance26 Jul
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  5. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  6. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  9. 2020Denoising Diffusion Implicit Models6 Oct
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 29

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  3. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  4. 2022Video Diffusion Modelscited by 2,305
  5. 2014Conditional Generative Adversarial Netscited by 2,162
  6. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  7. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  8. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  9. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  10. 2022Online Decision Transformercited by 196
  11. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 169
  12. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speechcited by 157
17 more
  1. 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 127
  2. 2019Conditioning by adaptive sampling for robust designcited by 111
  3. 2022Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimizationcited by 97
  4. 2023Leaving Reality to Imagination: Robust Classification via Generated Datasetscited by 91
  5. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 88
  6. 2021Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidancecited by 84
  7. 2019Model Inversion Networks for Model-Based Optimizationcited by 83
  8. 2020Autofocused oracles for model-based designcited by 50
  9. 2022Neural Diffusion Processescited by 50
  10. 2016On Explore-Then-Commit Strategiescited by 47
  11. 2022Masked Autoencoding for Scalable and Generalizable Decision Makingcited by 45
  12. 2022Generative Pretraining for Black-Box Optimizationcited by 36
  13. 2023Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RLcited by 36
  14. 2018Best arm identification in multi-armed bandits with delayed feedbackcited by 29
  15. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 28
  16. 2021Learning from an Exploring Demonstrator: Optimal Reward Estimation for Banditscited by 8
  17. 2022Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 25; 2025: 29; 2026: 18.

76 papers.

Sort:

By area:

  1. 2024Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Reviewcited by 98
  2. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimizationcited by 73
  3. 2023Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimizationcited by 56
  4. 2024Feedback Efficient Online Fine-Tuning of Diffusion Modelscited by 53
  5. 2024Diffusion Models as Constrained Samplers for Optimization with Unknown Constraintscited by 35
  6. 2026Diamond Maps: Efficient Reward Alignment via Stochastic Flow Mapscited by 29
  7. 2024LICO: Large Language Models for In-Context Molecular Optimizationcited by 26
  8. 2024Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Modelscited by 25
  9. 2024Diffusion Model for Data-Driven Black-Box Optimizationcited by 24
  10. 2023ExPT: Synthetic Pretraining for Few-Shot Experimental Designcited by 22
  11. 2024GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learningcited by 22
  12. 2024DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimizationcited by 20
38 more
  1. 2024Diffusion Models are Evolutionary Algorithmscited by 17
  2. 2025GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Modelscited by 17
  3. 2024Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimizationcited by 15
  4. 2025Generative Models in Decision Making: A Surveycited by 15
  5. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 15
  6. 2024Offline Multi-Objective Optimizationcited by 14
  7. 2024Pretrained Optimization Model for Zero-Shot Black Box Optimizationcited by 13
  8. 2024Offline Model-Based Optimization by Learning to Rankcited by 13
  9. 2024Diffusion Models as Network Optimizers: Explorations and Analysiscited by 13
  10. 2025Posterior Inference with Diffusion Models for High-dimensional Black-box Optimizationcited by 13
  11. 2025Preference-Guided Diffusion for Multi-Objective Offline Optimizationcited by 12
  12. 2024Constraint-Aware Diffusion Models for Trajectory Optimizationcited by 11
  13. 2024Generative Adversarial Model-Based Optimization via Source Critic Regularizationcited by 10
  14. 2024Expensive Multi-Objective Bayesian Optimization Based on Diffusion Modelscited by 10
  15. 2024Design Editing for Offline Model-based Optimizationcited by 10
  16. 2024"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihoodcited by 8
  17. 2024Robust Guided Diffusion for Offline Black-Box Optimizationcited by 8
  18. 2025Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generationcited by 7
  19. 2025Aligning Diffusion Model with Problem Constraints for Trajectory Optimizationcited by 7
  20. 2025Simplifying Bayesian Optimization Via In-Context Direct Optimum Samplingcited by 7
  21. 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddingscited by 7
  22. 2025Boosting Offline Optimizers with Surrogate Sensitivitycited by 6
  23. 2025Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniquescited by 5
  24. 2025ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problemscited by 5
  25. 2025Posterior Inference in Latent Space for Scalable Constrained Black-box Optimizationcited by 5
  26. 2025Diffusion-DFL: Decision-focused Diffusion Models for Stochastic Optimizationcited by 5
  27. 2024Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generationcited by 4
  28. 2024Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Spacecited by 4
  29. 2025ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridgecited by 4
  30. 2023Requirement falsification for cyber-physical systems using generative modelscited by 3
  31. 2024Cliqueformer: Model-Based Optimization with Structured Transformerscited by 3
  32. 2025Conformalized Decision Risk Assessmentcited by 3
  33. 2025BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewardscited by 3
  34. 2025Generative Bayesian Optimization: Generative Models as Acquisition Functionscited by 3
  35. 2025A Reward-Directed Diffusion Framework for Generative Design Optimizationcited by 2
  36. 2025SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusioncited by 2
  37. 2025A Gradient Guided Diffusion Framework for Chance Constrained Programmingcited by 2
  38. 2026Diffusion Large Language Models for Black-Box Optimizationcited by 2

50 most cited of 76 All 76 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization
  2. 2026Learning Where to Steer: Noise-Space Geometry for Efficient Offline Multi-Objective Optimization with Generative Models
  3. 2023Interpreting and Improving Diffusion Models from an Optimization Perspective
  4. 2025Low-dimensional adaptation of diffusion models: Convergence in total variation
  5. 2026Blind denoising diffusion models and the blessings of dimensionality
  6. 2026Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
  7. 2025A Denoising Diffusion-Based Evolutionary Algorithm Framework: Application to the Maximum Independent Set Problem
  8. 2025Meta-Black-Box-Optimization through Offline Q-function Learning