Denoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale Complexity

• URL: http://arxiv.org/abs/2411.01629v1
• Date: Sun, 03 Nov 2024 16:47:05 GMT
• Title: Denoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale Complexity
• Abstract summary: Diffusion-based generative models aim to denoise a Langevin diffusion chain. We show that score denoising is the optimal backward map in transportation cost.
• Score: 5.075506385456813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adding noise is easy; what about denoising? Diffusion is easy; what about reverting a diffusion? Diffusion-based generative models aim to denoise a Langevin diffusion chain, moving from a log-concave equilibrium measure $\nu$, say isotropic Gaussian, back to a complex, possibly non-log-concave initial measure $\mu$. The score function performs denoising, going backward in time, predicting the conditional mean of the past location given the current. We show that score denoising is the optimal backward map in transportation cost. What is its localization uncertainty? We show that the curvature function determines this localization uncertainty, measured as the conditional variance of the past location given the current. We study in this paper the effectiveness of the diffuse-then-denoise process: the contraction of the forward diffusion chain, offset by the possible expansion of the backward denoising chain, governs the denoising difficulty. For any initial measure $\mu$, we prove that this offset net contraction at time $t$ is characterized by the curvature complexity of a smoothed $\mu$ at a specific signal-to-noise ratio (SNR) scale $r(t)$. We discover that the multi-scale curvature complexity collectively determines the difficulty of the denoising chain. Our multi-scale complexity quantifies a fine-grained notion of average-case curvature instead of the worst-case. Curiously, it depends on an integrated tail function, measuring the relative mass of locations with positive curvature versus those with negative curvature; denoising at a specific SNR scale is easy if such an integrated tail is light. We conclude with several non-log-concave examples to demonstrate how the multi-scale complexity probes the bottleneck SNR for the diffuse-then-denoise process.

Related papers

• Posterior Information Dynamics of Diffusion Models for Linear Inverse Problems [11.548853370822343]
  We study the process through the smoothed likelihood force, the difference between exact posterior and prior scores at each noise level.<n>Averaging over measurements yields an information--minimum mean-square error (I-MMSE) identity linking information gain to denoising-error reduction.
  arXiv  Detail & Related papers  (2026-08-22T00:53:42Z)
• Nonparametric Deconvolution and Denoising using Simulation Based Inference [3.6640504352010885]
  We learn a latent generative model by matching the observed data distribution to the noise-convolved model distribution.<n>Our method provides a practical, theoretically grounded approach to deconvolution under generative latent distribution models.
  arXiv  Detail & Related papers  (2026-06-20T07:03:37Z)
• Sampling Data with Chains of Forward-Backward Diffusion Steps [7.829352305480285]
  We introduce U-turn chains, in which each step proposes a move that remains on the learned data manifold.<n>We show that minimal U-turn dynamics undergoes an ergodicity-breaking phase transition driven by fragmentation of the data manifold.<n>We discuss the implications of these results for sampling with diffusion models.
  arXiv  Detail & Related papers  (2026-05-26T13:26:36Z)
• Sample Complexity of Policy Gradient for Log-Growth Control [23.86784769848408]
  We study the sample complexity of policy gradient for log-growth control.<n>We prove that projected mini-batch policy gradient attains total sample complexity.
  arXiv  Detail & Related papers  (2026-05-26T07:24:14Z)
• The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning [20.547812775989808]
  We study autonomous (noise-agnostic) generative models, such as Equilibrium Matching and blind diffusion.<n>We prove that generation using autonomous models is not merely blind denoising.<n>We also establish the structural stability conditions for sampling with autonomous models.
  arXiv  Detail & Related papers  (2026-02-20T18:49:00Z)
• Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study [3.265950484493743]
  Diffusion models can be prone to memorization.<n>Regularization on the score has the same effect as increasing the size of the training dataset.<n>This perspective highlights two regularization mechanisms taking place in denoising diffusions.
  arXiv  Detail & Related papers  (2025-05-28T20:22:18Z)
• Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation [0.0]
  dependencies between intermediate noisy states lead to error accumulation and propagation during the reverse denoising process.<n>We propose a novel framework called Simple Iterative Denoising, which simplifies discrete diffusion and circumvents the issue.<n>Our empirical evaluations demonstrate that the proposed method significantly outperforms existing discrete diffusion baselines in graph generation tasks.
  arXiv  Detail & Related papers  (2025-03-27T15:08:58Z)
• Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs [25.784316302130875]
  Covariance information is available for free from training data and the curvature of the generative trajectory. We integrate these sources of information using em (i) a novel method to transfer covariance estimates across noise levels. We validate the method on linear inverse problems, where it outperforms recent baselines.
  arXiv  Detail & Related papers  (2024-10-15T00:23:09Z)
• Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel [12.464924018243988]
  Recent work has shown that training wide neural networks with gradient descent is formally equivalent to computing the mean of the posterior distribution in a Gaussian Process. We show how to deal with non-zero aleatoric noise and derive an estimator for the posterior covariance.
  arXiv  Detail & Related papers  (2024-09-06T00:34:44Z)
• Non-asymptotic bounds for forward processes in denoising diffusions: Ornstein-Uhlenbeck is hard to beat [49.1574468325115]
  This paper presents explicit non-asymptotic bounds on the forward diffusion error in total variation (TV) We parametrise multi-modal data distributions in terms of the distance $R$ to their furthest modes and consider forward diffusions with additive and multiplicative noise.
  arXiv  Detail & Related papers  (2024-08-25T10:28:31Z)
• Listening to the Noise: Blind Denoising with Gibbs Diffusion [4.310554658046964]
  We develop a Gibbs algorithm that alternates sampling steps from a conditional diffusion model trained to map the signal prior to the family of noise distributions. Our theoretical analysis highlights potential pitfalls, guides diagnostic usage, and quantifies errors in the Gibbs stationary distribution. We showcase our method for 1) blind denoising of natural images involving colored noises with unknown amplitude and spectral index, and 2) a cosmology problem, where Bayesian inference of "noise" parameters means constraining models of the evolution of the Universe.
  arXiv  Detail & Related papers  (2024-02-29T18:50:11Z)
• Revisiting Convergence of AdaGrad with Relaxed Assumptions [4.189643331553922]
  We revisit the convergence of AdaGrad with momentum (covering AdaGrad as a special case) on problems. This model encompasses a broad range noises including sub-auau in many practical applications.
  arXiv  Detail & Related papers  (2024-02-21T13:24:14Z)
• Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems [56.86067111855056]
  We consider clipped optimization problems with heavy-tailed noise with structured density. We show that it is possible to get faster rates of convergence than $mathcalO(K-(alpha - 1)/alpha)$, when the gradients have finite moments of order. We prove that the resulting estimates have negligible bias and controllable variance.
  arXiv  Detail & Related papers  (2023-11-07T17:39:17Z)
• PENDANTSS: PEnalized Norm-ratios Disentangling Additive Noise, Trend and Sparse Spikes [1.9766522384767222]
  We propose PENDANTSS for joint trend removal and blind deconvolution of sparse peak-like signals. It blends a parsimonious prior with the hypothesis that smooth trend and noise can somewhat be separated by low-pass filtering.
  arXiv  Detail & Related papers  (2023-01-04T10:11:21Z)
• A Data-driven Loss Weighting Scheme across Heterogeneous Tasks for Image Denoising [67.02529586335473]
  In variational denoising models, weight in the data fidelity term plays the role of enhancing the noise-removal capability.<n>In this work, we propose a data-driven loss weighting scheme to address these issues.<n> Numerical results verify the remarkable performance of DLW on improving the ability of various variational denoising models to handle different complex noise.
  arXiv  Detail & Related papers  (2022-12-09T03:28:07Z)
• Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
  We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling. Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
  arXiv  Detail & Related papers  (2022-09-29T11:12:27Z)
• Identifying Hard Noise in Long-Tailed Sample Distribution [76.16113794808001]
  We introduce Noisy Long-Tailed Classification (NLT) Most de-noising methods fail to identify the hard noises. We design an iterative noisy learning framework called Hard-to-Easy (H2E)
  arXiv  Detail & Related papers  (2022-07-27T09:03:03Z)
• The Optimal Noise in Noise-Contrastive Learning Is Not What You Think [80.07065346699005]
  We show that deviating from this assumption can actually lead to better statistical estimators. In particular, the optimal noise distribution is different from the data's and even from a different family.
  arXiv  Detail & Related papers  (2022-03-02T13:59:20Z)
• Debiased Sinkhorn barycenters [110.79706180350507]
  Entropy regularization in optimal transport (OT) has been the driver of many recent interests for Wasserstein metrics and barycenters in machine learning. We show how this bias is tightly linked to the reference measure that defines the entropy regularizer. We propose debiased Wasserstein barycenters that preserve the best of both worlds: fast Sinkhorn-like iterations without entropy smoothing.
  arXiv  Detail & Related papers  (2020-06-03T23:06:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.