mlsanityData to 14 Oct 2026

Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems

arXiv 2206.09104 ↗First posted 18 Jun 2022cs.LG cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

We prove fast mixing and characterize the stationary distribution of the Langevin Algorithm for inverting random weighted DNN generators. This result extends the work of Hand and Voroninski from efficient inversion to efficient posterior sampling. In practice, to allow for increased expressivity, we propose to do posterior sampling in the latent space of a pre-trained generative model. To achieve that, we train a score-based model in the latent space of a StyleGAN-2 and we use it to solve inverse problems. Our framework, Score-Guided Intermediate Layer Optimization (SGILO), extends prior work by replacing the sparsity regularization with a generative prior in the intermediate layer. Experimentally, we obtain significant improvements over the previous state-of-the-art, especially in the low measurement regime.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 61 of its 74 references that are in the map. First posted on arXiv 18 Jun 2022.

Builds on

61 of 74 references.

References · 61

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  10. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
38 more
  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  3. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  7. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  8. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  9. 2021Score-based Generative Modeling in Latent Spacecited by 636
  10. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  11. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 521
  12. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  13. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  14. 2017Compressed Sensing using Generative Modelscited by 339
  15. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 291
  16. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 286
  17. 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 243
  18. 2021Gotta Go Fast When Generating Data with Score-Based Modelscited by 219
  19. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  20. 2018Deep Learning for Single Image Super-Resolution: A Brief Reviewcited by 158
  21. 2019Seeing What a GAN Cannot Generatecited by 148
  22. 2021Learning to Efficiently Sample from Diffusion Probabilistic Modelscited by 129
  23. 2019Deep Learning on Image Denoising: An overviewcited by 128
  24. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  25. 2017Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimizationcited by 97
  26. 2019Theoretical guarantees for sampling and inference in generative models with latent diffusionscited by 97
  27. 2019Coherent Semantic Attention for Image Inpaintingcited by 97
  28. 2019Invertible generative models for inverse problems: mitigating representation error and dataset biascited by 94
  29. 2018Phase Retrieval Under a Generative Priorcited by 73
  30. 2021Intermediate Layer Optimization for Inverse Problems using Deep Generative Modelscited by 70
  31. 2019Learned Image Downscaling for Upscaling using Content Adaptive Resamplercited by 55
  32. 2021Measuring Robustness in Deep Learning Based Compressive Sensingcited by 53
  33. 20223D GAN Inversion for Controllable Portrait Image Animationcited by 53
  34. 2021Instance-Optimal Compressed Sensing via Posterior Samplingcited by 43
  35. 2017Global Guarantees for Enforcing Deep Generative Priors by Empirical Riskcited by 37
  36. 2018Modeling Sparse Deviations for Compressed Sensing using Generative Modelscited by 33
  37. 2019Block Coordinate Regularization by Denoisingcited by 33
  38. 2021Fairness for Image Generation with Uncertain Sensitive Attributescited by 31

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 5; 2024: 2; 2025: 1.

11 papers.

  1. 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Modelscited by 157
  2. 2022Soft Diffusion: Score Matching for General Corruptionscited by 102
  3. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 77
  4. 2023Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplerscited by 74
  5. 2023Prompt-tuning latent diffusion models for inverse problemscited by 70
  6. 2023Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistentcited by 58
  7. 2022Multiresolution Textual Inversioncited by 34
  8. 2024Idempotence and Perceptual Image Compressioncited by 29
  9. 2023Robust Unsupervised StyleGAN Image Restorationcited by 14
  10. 2025Multitask Learning with Stochastic Interpolantscited by 3
  11. 2024Bi-level Guided Diffusion Models for Zero-Shot Medical Imaging Inverse Problemscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Preconditioned Score-based Generative Models
  2. 2022Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling
  3. 2024Score-based Generative Models with Adaptive Momentum
  4. 2023A Complete Recipe for Diffusion Generative Models
  5. 2026Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models
  6. 2025Preconditioned Langevin Dynamics with Score-Based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems
  7. 2024Posterior sampling via Langevin dynamics based on generative priors
  8. 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data