arxiv: 2605.13278 · v1 · submitted 2026-05-13 · 🧮 math.OC · cs.LG

Recognition: unknown

Proximal-Based Generative Modeling for Bayesian Inverse Problems

Boyang Zhang, Ya-Feng Liu, Zhiguo Wang

Authors on Pith no claims yet

Pith reviewed 2026-05-14 17:50 UTC · model grok-4.3

classification 🧮 math.OC cs.LG

keywords diffusiongenerativescoredemonstrateframeworkinverselikelihoodmodeling

0 comments

The pith

PGM replaces the intractable likelihood score in diffusion models with a closed-form Moreau score computed via proximal operators, enabling non-asymptotic sampling for inverse problems trained only on prior data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Diffusion models work by gradually adding noise to data and then learning to reverse that process. For inverse problems such as recovering a clean signal from noisy or incomplete measurements, the reversal step requires knowing how the measurements affect the score, which is usually impossible to compute directly. The authors observe that adding Gaussian noise is mathematically the same as applying a smoothing operation known as Moreau-Yosida regularization from optimization theory. This equivalence lets them define a new Moreau score that can be evaluated exactly using proximal operators, standard tools that solve simple optimization subproblems. They then train these operators by matching the Moreau score using only samples drawn from the prior distribution, without ever seeing the measurement data during training. The resulting sampler runs without the early stopping that previous diffusion methods needed to avoid bias and is reported to converge at a non-asymptotic rate.

Core claim

PGM eliminates the early-stopping bias inherent in the score-based diffusion model and achieves non-asymptotic convergence.

Load-bearing premise

The theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization holds rigorously and directly yields a closed-form Moreau score via proximal operators that can be learned from prior samples alone.

Figures

Figures reproduced from arXiv: 2605.13278 by Boyang Zhang, Ya-Feng Liu, Zhiguo Wang.

**Figure 1.** Figure 1: A sketch map for PGM. Training phase: a proximal splitting is applied to provide an approximation of the Moreau score, where a network is trained to learn the proximal operator in an unsupervised manner. Sampling phase: the traditional score function is replaced by the Moreau score, which admits an explicit, smooth, and asymptotically equivalent formulation via proximal operators. Recent years have witness… view at source ↗

**Figure 2.** Figure 2: Sampling error decomposition. where D1 = We( √ d + diam(X )), D2 = 1 + Weλ −1 diam2 (X )Mλ mλ − Mµ Wλ, D3 = 1 + Weλ −1 diam2 (X )Mλ mλ − Mµ (Wf + Wµ), with some bounded constants We, Wλ, Wµ, Wf . It is worth noting that the error W1 (Law(x¯K), π) vanishes as T → ∞, M → 0, and δ → 0. Consequently, Theorem 4.3 extends classical convergence results for diffusion models (De Bortoli, 2022; Khalaf… view at source ↗

**Figure 3.** Figure 3: Sampling from truncated normal distribution. Score-based methods (a) DDPM and (b) Projected diffusion model fail to handle constraint. Proximal-based methods (c) proximal Langevin and (d) PGM (Our) perform better. PGM achieves better feasibility (inside-ratio= 98.45%) and optimality (peak at x = −0.02). 5. Experiments In this section, we validate the practical performance of PGM through two experiments. To… view at source ↗

**Figure 4.** Figure 4: Visual samples for LSUN-Bedroom. in terms of structural information—a crucial measure for high-quality image restoration. 5.4. Visualizing Confirmation To evaluate the cross-prior generalization capability of PGM, we execute additional tests on the LSUN-Bedroom datasets. Qualitative results on LSUN-Bedroom are displayed in Figure 4, visually confirming the model’s capability to generate high-fidelity and … view at source ↗

**Figure 5.** Figure 5: Samples for MNIST (first line: original images, second line: measurements, third line: reconstructed images). B.4. Additional Results on Human Face Reconstruction Qualitative results on FFHQ and CelebA-HQ are displayed in Figures 6 and 7, respectively, visually confirming the model’s capability to generate high-fidelity and natural-looking images [PITH_FULL_IMAGE:figures/full_fig_p021_5.png] view at source ↗

**Figure 6.** Figure 6: Samples for FFHQ (first line: original images, second line: measurements, third line: reconstructed images). Further, we provide the Pareto front to compare the trade-off between reconstruction quality and inference time. In [PITH_FULL_IMAGE:figures/full_fig_p021_6.png] view at source ↗

**Figure 7.** Figure 7: Samples for CelebA-HQ (first line: original images, second line: measurements, third line: reconstructed images) [PITH_FULL_IMAGE:figures/full_fig_p022_7.png] view at source ↗

**Figure 8.** Figure 8: Trade-off between reconstruction quality and inference time. 2024; Zhang et al., 2025a; Zirvi et al., 2025). Based on the quantitative results on ImageNet-100, our proposed PGM achieves competitive performance across three inverse problems. For super resolution and inpainting, PGM attains the highest PSNR while DiffStateGrad-DAPS obtains the best LPIPS. For Gaussian deblurring, PGM obtains the best LPIPS a… view at source ↗

read the original abstract

Score-based diffusion models demonstrate superior performance in generative tasks but encounter fundamental bottlenecks in inverse problems due to the analytical intractability of the time-dependent likelihood score. To bridge this gap, we propose a novel proximal-based generative modeling (PGM) framework that rigorously circumvents explicit likelihood evaluation. Our framework is built upon a theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization in nonsmooth optimization. This enables a new sampling mechanism driven by the proposed Moreau score, which admits a closed-form expression via proximal operators. Moreover, we introduce Moreau score matching to learn the proximal operators that rely solely on samples drawn from the prior distribution. Theoretically, PGM eliminates the early-stopping bias inherent in the score-based diffusion model and achieves non-asymptotic convergence. Experiments demonstrate that PGM significantly surpasses state-of-the-art methods in reconstruction quality and sampling time.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper links diffusion to proximal operators via a Moreau score learned only from prior samples to sidestep likelihood intractability in inverse problems, but the non-asymptotic posterior convergence claim needs verification on exactly how data enters the dynamics.

read the letter

The core idea here is a proximal-based generative modeling framework that equates Gaussian convolution in diffusion with Moreau-Yosida regularization. This produces a closed-form Moreau score expressed through proximal operators, which they learn via a matching objective using only prior samples. The result is a sampling method for Bayesian inverse problems that avoids explicit likelihood evaluation, with claims of removing early-stopping bias and delivering non-asymptotic convergence. Experiments report better reconstruction quality and shorter sampling times than current approaches. What stands out as new is the direct construction of the score from proximal maps rather than fitting a neural network to the usual score function. This draws on optimization theory in a way that feels like a targeted fix for the intractability that blocks diffusion models in imaging and reconstruction tasks. The paper does a solid job naming the practical bottleneck and showing a training procedure that stays prior-only, which could simplify workflows where the forward model is known but the likelihood remains messy. The soft spots sit mainly in the theoretical step from equivalence to exact posterior sampling. The abstract presents the equivalence as rigorous, yet the mechanism for folding in the data term while preserving closed-form behavior and non-asymptotic guarantees is not spelled out at this level. If the likelihood enters through an auxiliary proximal step or approximation, the convergence property could weaken, and the stress-test concern about implicit handling is worth pressing. Full derivations and error analysis would clarify whether the claims hold without hidden biases. The experimental summary is high-level, so details on baselines, metrics, and failure cases would help. The citations follow standard lines from score-based diffusion and proximal optimization without obvious gaps or circularity. This work is aimed at researchers combining generative models with scientific inverse problems. A reader looking for alternatives to standard diffusion sampling in Bayesian settings would get concrete ideas to test, even if parts need adaptation. The thinking is coherent and engages the literature directly, so the paper deserves peer review to examine the proofs and implementation details. I would send it to referees rather than desk-reject.

Referee Report

2 major / 2 minor

Summary. The manuscript proposes a Proximal-Based Generative Modeling (PGM) framework for Bayesian inverse problems. It establishes a theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization, enabling a closed-form Moreau score expressed via proximal operators. These operators are learned solely from prior samples using Moreau score matching, avoiding explicit likelihood evaluation. The framework claims to remove early-stopping bias from score-based diffusion models and deliver non-asymptotic convergence, with experiments indicating superior reconstruction quality and faster sampling times compared to existing methods.

Significance. If the equivalence rigorously extends to posterior sampling and the non-asymptotic convergence holds, the work would meaningfully advance generative approaches to inverse problems by linking diffusion models with proximal optimization. This could yield more stable and efficient sampling in applications such as imaging and tomography, where likelihood scores are intractable. The ability to train exclusively on prior samples while targeting the posterior would be a notable practical advantage over standard score-matching techniques.

major comments (2)

[Theoretical Framework] The central claim that the Moreau score can be learned from prior samples alone while correctly sampling the posterior requires explicit handling of the likelihood term. The abstract states that the framework circumvents explicit likelihood evaluation, but provides no mechanism (e.g., an auxiliary proximal step or modified operator) for incorporating the data-dependent term into the sampling dynamics. This is load-bearing for the posterior-sampling guarantee.
[§4] §4 (Convergence Analysis): The non-asymptotic convergence result and elimination of early-stopping bias are asserted without visible error bounds, rate statements, or assumptions on the proximal operator approximation. A concrete theorem stating the distance to the target posterior after finite steps is needed to substantiate the claim.

minor comments (2)

[Introduction] Notation for the Moreau score and proximal operator should be introduced with a brief reminder of the standard definition (e.g., prox_λf) at first use to aid readers unfamiliar with nonsmooth optimization.
[Experiments] The experimental section would benefit from a table summarizing forward operators, noise levels, and dataset sizes across all compared methods to allow direct assessment of fairness.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the thorough review and valuable feedback on our manuscript. The comments have prompted us to strengthen the theoretical exposition. We address each major comment below, indicating the revisions we plan to make.

read point-by-point responses

Referee: [Theoretical Framework] The central claim that the Moreau score can be learned from prior samples alone while correctly sampling the posterior requires explicit handling of the likelihood term. The abstract states that the framework circumvents explicit likelihood evaluation, but provides no mechanism (e.g., an auxiliary proximal step or modified operator) for incorporating the data-dependent term into the sampling dynamics. This is load-bearing for the posterior-sampling guarantee.

Authors: We agree that the mechanism for incorporating the data-dependent term must be made explicit to support the posterior sampling claim. In the original manuscript, the sampling procedure (detailed in Section 3) uses the learned Moreau score for the prior potential combined with a proximal step for the data fidelity term, leveraging the fact that the proximal operator of the composite objective can be computed without evaluating the likelihood score directly. However, we acknowledge that this decomposition was not sufficiently highlighted. In the revised version, we will expand Section 3 with a new subsection explaining the sampling dynamics: the update rule integrates the Moreau score (from prior) and applies the proximal operator of the negative log-likelihood (which is closed-form for standard inverse problems). We will also add a remark clarifying how this avoids explicit score computation while targeting the posterior. This revision will include a diagram of the algorithm flow for clarity. revision: yes
Referee: [§4] §4 (Convergence Analysis): The non-asymptotic convergence result and elimination of early-stopping bias are asserted without visible error bounds, rate statements, or assumptions on the proximal operator approximation. A concrete theorem stating the distance to the target posterior after finite steps is needed to substantiate the claim.

Authors: We concur that the convergence analysis requires more precise statements to fully substantiate the non-asymptotic claims. The current Section 4 presents a theorem bounding the sampling error in terms of the proximal operator approximation error, but the explicit dependence on the number of discretization steps and the specific assumptions (such as strong convexity or Lipschitz continuity of the proximal mapping) are implicit rather than stated upfront. In the revision, we will reformulate Theorem 4.1 to explicitly state the error bound, e.g., the total variation distance to the target posterior is at most C * (1/sqrt(N) + ε), where N is the number of steps and ε is the approximation error, under the assumption that the proximal operator is approximated within ε in the sup norm. We will also add a dedicated paragraph on the elimination of early-stopping bias, showing that the bias term vanishes as the terminal time T → ∞ independently of the discretization. These changes will be accompanied by the necessary proof sketches in the appendix. revision: yes

Circularity Check

0 steps flagged

No circularity; derivation rests on external equivalence and prior-sample learning

full rationale

The paper's core chain begins with the stated equivalence between Gaussian convolution and Moreau-Yosida regularization, treated as an external fact from optimization theory rather than a self-derived relation. This yields a closed-form Moreau score via proximal operators, which are then learned by Moreau score matching using only samples from the prior distribution. The non-asymptotic convergence claim and elimination of early-stopping bias follow directly from the resulting sampling dynamics under this equivalence, without any step in which a prediction or result is defined in terms of itself, a fitted parameter from the target posterior, or a load-bearing self-citation. No ansatz is smuggled via prior work, and the likelihood incorporation for the inverse problem is handled through the proximal construction without reducing the central quantities to tautological inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim rests on the stated equivalence between diffusion convolution and Moreau-Yosida regularization plus the assumption that proximal operators learned from prior samples suffice for the inverse problem.

axioms (1)

domain assumption Equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization
Invoked as the theoretical foundation that enables the closed-form Moreau score.

invented entities (1)

Moreau score no independent evidence
purpose: Drives the generative sampling step in place of the intractable likelihood score
Defined via proximal operators; no independent falsifiable evidence provided in abstract.

pith-pipeline@v0.9.0 · 5443 in / 1238 out tokens · 41732 ms · 2026-05-14T17:50:32.559283+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

132 extracted references · 34 canonical work pages · 4 internal anchors

[1]

Proceedings of the 28th International Conference on Machine Learning , pages=

Bayesian Learning via Stochastic Gradient Langevin Dynamics , author=. Proceedings of the 28th International Conference on Machine Learning , pages=
[2]

Score-Based Generative Modeling through Stochastic Differential Equations

Score-Based Generative Modeling through Stochastic Differential Equations , author=. arXiv preprint arXiv:2011.13456 , year=

work page internal anchor Pith review Pith/arXiv arXiv 2011
[3]

SIAM Review , volume=

A Proximal Markov Chain Monte Carlo Method for Bayesian Inference in Imaging Inverse Problems: When Langevin Meets Moreau , author=. SIAM Review , volume=. 2022 , publisher=

2022
[4]

Advances in Neural Information Processing Systems , volume=

Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization , author=. Advances in Neural Information Processing Systems , volume=
[5]

2013 , publisher=

Statistical Physics: Volume 5 , author=. 2013 , publisher=

2013
[6]

Advances in Neural Information Processing Systems , volume=

Implicit Generation and Modeling with Energy Based Models , author=. Advances in Neural Information Processing Systems , volume=
[7]

Journal of the Royal Statistical Society: Series B (Methodological) , volume=

Estimation of Finite Mixture Distributions through Bayesian Sampling , author=. Journal of the Royal Statistical Society: Series B (Methodological) , volume=. 1994 , publisher=

1994
[8]

The Annals of Applied Probability , volume=

Nonasymptotic Convergence Analysis for the Unadjusted Langevin Algorithm , author=. The Annals of Applied Probability , volume=
[9]

Bernoulli , volume=

Exponential Convergence of Langevin Distributions and Their Discrete Approximations , author=. Bernoulli , volume=
[10]

Statistics and Computing , volume=

Proximal Markov Chain Monte Carlo Algorithms , author=. Statistics and Computing , volume=. 2016 , publisher=

2016
[11]

Advances in Neural Information Processing Systems , volume=

Mirrored Langevin Dynamics , author=. Advances in Neural Information Processing Systems , volume=
[12]

Advances in Neural Information Processing Systems , volume=

Denoising Diffusion Probabilistic Models , author=. Advances in Neural Information Processing Systems , volume=
[13]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

High-Resolution Image Synthesis with Latent Diffusion Models , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
[14]

Advances in Neural Information Processing Systems , volume=

Diffusion Models Beat GANs on Image Synthesis , author=. Advances in Neural Information Processing Systems , volume=
[15]

International Conference on Machine Learning , pages=

Diffusion Models for Black-Box Optimization , author=. International Conference on Machine Learning , pages=. 2023 , organization=

2023
[16]

arXiv preprint arXiv:2403.13219 , year=

Diffusion Model for Data-Driven Black-Box Optimization , author=. arXiv preprint arXiv:2403.13219 , year=

work page arXiv
[17]

Advances in Neural Information Processing Systems , volume=

Gradient Guidance for Diffusion Models: An Optimization Perspective , author=. Advances in Neural Information Processing Systems , volume=
[18]

arXiv preprint arXiv:2510.12238 , year=

A Gradient Guided Diffusion Framework for Chance Constrained Programming , author=. arXiv preprint arXiv:2510.12238 , year=

work page arXiv
[19]

Advances in Neural Information Processing Systems , volume=

A Gradient Guided Diffusion Framework for Chance Constrained Programming , author=. Advances in Neural Information Processing Systems , volume=
[20]

Advances in Neural Information Processing Systems , volume=

Mirror Diffusion Models for Constrained and Watermarked Generation , author=. Advances in Neural Information Processing Systems , volume=
[21]

arXiv preprint arXiv:2402.18012 , year=

Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints , author=. arXiv preprint arXiv:2402.18012 , year=

work page arXiv
[22]

Advances in Neural Information Processing Systems , volume=

Constrained Synthesis with Projected Diffusion Models , author=. Advances in Neural Information Processing Systems , volume=
[23]

International Conference on Machine Learning , pages=

Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis for DDIM-Type Samplers , author=. International Conference on Machine Learning , pages=. 2023 , organization=

2023
[24]

arXiv preprint arXiv:2306.09251 , year=

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models , author=. arXiv preprint arXiv:2306.09251 , year=

work page arXiv
[25]

Advances in Neural Information Processing Systems , volume=

Convergence for Score-Based Generative Modeling with Polynomial Complexity , author=. Advances in Neural Information Processing Systems , volume=
[26]

arXiv preprint arXiv:2209.11215 , year=

Sampling Is as Easy as Learning the Score: Theory for Diffusion Models with Minimal Data Assumptions , author=. arXiv preprint arXiv:2209.11215 , year=

work page arXiv
[27]

Auto-Encoding Variational Bayes

Auto-Encoding Variational Bayes , author=. arXiv preprint arXiv:1312.6114 , year=

work page internal anchor Pith review Pith/arXiv arXiv
[28]

Advances in Neural Information Processing Systems , volume=

Generating Diverse High-Fidelity Images with VQ-VAE-2 , author=. Advances in Neural Information Processing Systems , volume=
[29]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
[30]

Nature Communications , volume=

-Variational Autoencoders and Transformers for Reduced-Order Modelling of Fluid Flows , author=. Nature Communications , volume=. 2024 , publisher=

2024
[31]

arXiv preprint arXiv:2511.00338 , year=

A DeepONet Joint Neural Tangent Kernel Hybrid Framework for Physics-Informed Inverse Source Problems and Robust Image Reconstruction , author=. arXiv preprint arXiv:2511.00338 , year=

work page arXiv
[32]

1998 , publisher=

Variational Analysis , author=. 1998 , publisher=

1998
[33]

Journal of the American Statistical Association , volume=

Tweedie’s Formula and Selection Bias , author=. Journal of the American Statistical Association , volume=. 2011 , publisher=

2011
[34]

On Extensions of the Brunn-Minkowski and Pr

Brascamp, Herm Jan and Lieb, Elliott H , journal=. On Extensions of the Brunn-Minkowski and Pr. 1976 , publisher=

1976
[35]

The Annals of Statistics , pages=

Estimation of the Mean of a Multivariate Normal Distribution , author=. The Annals of Statistics , pages=. 1981 , publisher=

1981
[36]

Backward It

Del Moral, Pierre and Singh, Sumeetpal Sidhu , journal=. Backward It. 2022 , publisher=

2022
[37]

Stochastic Integral , author=

109. Stochastic Integral , author=. Proceedings of the Imperial Academy , volume=. 1944 , publisher=

1944
[38]

Conference on Learning Theory , pages=

Convergence Rates and Approximation Results for SGD and Its Continuous-Time Counterpart , author=. Conference on Learning Theory , pages=. 2021 , organization=

2021
[39]

arXiv preprint arXiv:2510.23552 , year=

Generalized Kantorovich-Rubinstein Duality beyond Hausdorff and Kantorovich , author=. arXiv preprint arXiv:2510.23552 , year=

work page arXiv
[40]

Journal of Machine Learning Research , volume=

An Efficient Sampling Algorithm for Non-Smooth Composite Potentials , author=. Journal of Machine Learning Research , volume=
[41]

Proceedings of the National Academy of Sciences , volume=

Sampling Can Be Faster Than Optimization , author=. Proceedings of the National Academy of Sciences , volume=. 2019 , publisher=

2019
[42]

Advances in Neural Information Processing Systems , volume=

Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates , author=. Advances in Neural Information Processing Systems , volume=
[43]

Journal of Machine Learning Research , volume=

Optimal Scaling for the Proximal Langevin Algorithm in High Dimensions , author=. Journal of Machine Learning Research , volume=
[44]

Advances in Neural Information Processing Systems , volume=

Efficient Constrained Sampling via the Mirror-Langevin Algorithm , author=. Advances in Neural Information Processing Systems , volume=
[45]

arXiv preprint arXiv:2307.08123 , year=

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency , author=. arXiv preprint arXiv:2307.08123 , year=

work page arXiv
[46]

IEEE Communications Magazine , volume=

DiffSG: A Generative Solver for Network Optimization with Diffusion Model , author=. IEEE Communications Magazine , volume=. 2025 , publisher=

2025
[47]

Advances in Neural Information Processing Systems , volume=

Difusco: Graph-Based Diffusion Solvers for Combinatorial Optimization , author=. Advances in Neural Information Processing Systems , volume=
[48]

Advances in Neural Information Processing Systems , volume=

Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization , author=. Advances in Neural Information Processing Systems , volume=
[49]

Advances in Neural Information Processing Systems , volume=

Constrained Diffusion Models via Dual Training , author=. Advances in Neural Information Processing Systems , volume=
[50]

Advances in Neural Information Processing Systems , volume=

Improving Diffusion Models for Inverse Problems Using Manifold Constraints , author=. Advances in Neural Information Processing Systems , volume=
[51]

arXiv preprint arXiv:2403.03852 , year=

Accelerating Convergence of Score-Based Diffusion Models, Provably , author=. arXiv preprint arXiv:2403.03852 , year=

work page arXiv
[52]

arXiv preprint arXiv:2208.05314 , year=

Convergence of Denoising Diffusion Models under the Manifold Hypothesis , author=. arXiv preprint arXiv:2208.05314 , year=

work page arXiv
[53]

IEEE Transactions on Pattern Analysis and Machine Intelligence , volume=

Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , author=. IEEE Transactions on Pattern Analysis and Machine Intelligence , volume=. 1984 , publisher=

1984
[54]

arXiv preprint arXiv:2310.14344 , year=

What's in a Prior? Learned Proximal Networks for Inverse Problems , author=. arXiv preprint arXiv:2310.14344 , year=

work page arXiv
[55]

arXiv preprint arXiv:2507.08956 , year=

Beyond Scores: Proximal Diffusion Models , author=. arXiv preprint arXiv:2507.08956 , year=

work page arXiv
[56]

arXiv preprint arXiv:2503.09790 , year=

Constrained Discrete Diffusion , author=. arXiv preprint arXiv:2503.09790 , year=

work page arXiv
[57]

2024 , booktitle=

Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models , author=. 2024 , booktitle=

2024
[58]

Diffusion Posterior Sampling for General Noisy Inverse Problems

Diffusion Posterior Sampling for General Noisy Inverse Problems , author=. arXiv preprint arXiv:2209.14687 , year=

work page internal anchor Pith review Pith/arXiv arXiv
[59]

International Conference on Learning Representations , year=

Pseudoinverse-Guided Diffusion Models for Inverse Problems , author=. International Conference on Learning Representations , year=
[60]

SIAM Journal on Imaging Sciences , volume=

Efficient Diffusion Posterior Sampling for Noisy Inverse Problems , author=. SIAM Journal on Imaging Sciences , volume=. 2025 , publisher=

2025
[61]

SIAM Journal on Control and Optimization , volume=

Monotone Operators and the Proximal Point Algorithm , author=. SIAM Journal on Control and Optimization , volume=. 1976 , publisher=

1976
[62]

SIAM Review , volume=

Proximal Splitting Algorithms for Convex Optimization: A Tour of Recent Advances, with New Twists , author=. SIAM Review , volume=. 2023 , publisher=

2023
[63]

Mathematical Programming , volume=

On the Douglas--Rachford Splitting Method and the Proximal Point Algorithm for Maximal Monotone Operators , author=. Mathematical Programming , volume=. 1992 , publisher=

1992
[64]

International Conference on Machine Learning , pages=

Stochastic Gradient Descent for Non-Smooth Optimization: Convergence Results and Optimal Averaging Schemes , author=. International Conference on Machine Learning , pages=. 2013 , organization=

2013
[65]

arXiv preprint arXiv:2601.02499 , year=

Polynomial Convergence of Riemannian Diffusion Models , author=. arXiv preprint arXiv:2601.02499 , year=

work page arXiv
[66]

1993 , publisher=

Inverse Problems in the Mathematical Sciences , author=. 1993 , publisher=

1993
[67]

Proceedings of the IEEE , volume=

Computational Methods for Sparse Solution of Linear Inverse Problems , author=. Proceedings of the IEEE , volume=. 2010 , publisher=

2010
[68]

2021 , publisher=

Introduction to Inverse Problems in Imaging , author=. 2021 , publisher=

2021
[69]

IEEE Communications Letters , volume=

Deep Learning-Based Channel Estimation , author=. IEEE Communications Letters , volume=. 2019 , publisher=

2019
[70]

Journal of Machine Learning Research , volume=

Cascaded Diffusion Models for High Fidelity Image Generation , author=. Journal of Machine Learning Research , volume=
[71]

Acta Numerica , volume=

Inverse Problems: A Bayesian Perspective , author=. Acta Numerica , volume=. 2010 , publisher=

2010
[72]

2017 MATRIX Annals , pages=

Optimization Methods for Inverse Problems , author=. 2017 MATRIX Annals , pages=. 2019 , publisher=

2017
[73]

IEEE Transactions on Image Processing , volume=

An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems , author=. IEEE Transactions on Image Processing , volume=. 2010 , publisher=

2010
[74]

The Annals of Statistics , pages=

Bayesian Inverse Problems with Gaussian Priors , author=. The Annals of Statistics , pages=. 2011 , publisher=

2011
[75]

Advances in Neural Information Processing Systems , volume=

Generative Adversarial Nets , author=. Advances in Neural Information Processing Systems , volume=
[76]

Philosophical Transactions of the Royal Society A , volume=

Bridging Diffusion Posterior Sampling and Monte Carlo Methods: A Survey , author=. Philosophical Transactions of the Royal Society A , volume=. 2025 , publisher=

2025
[77]

Inverse Problems , volume=

On Optimization Techniques for Solving Nonlinear Inverse Problems , author=. Inverse Problems , volume=. 2000 , publisher=

2000
[78]

Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

Freedom: Training-Free Energy-Guided Conditional Diffusion Model , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=
[79]

Advances in Neural Information Processing Systems , volume=

Score-Based Generative Models Detect Manifolds , author=. Advances in Neural Information Processing Systems , volume=
[80]

arXiv preprint arXiv:2106.05527 , year=

Soft Truncation: A Universal Training Technique of Score-Based Diffusion Model for High Precision Score Estimation , author=. arXiv preprint arXiv:2106.05527 , year=

work page arXiv

Showing first 80 references.