From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models

• URL: http://arxiv.org/abs/2607.23226v1
• Date: Sat, 25 Jul 2026 14:24:38 GMT
• Title: From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models
• Abstract summary: We study how finite-sample learning, network parameterization, and numerical discretization jointly dictate generative quality.<n>Our results quantitatively characterize how the training sample size, temporal discretization grids, and optimization accuracy jointly control the final fidelity of samples generated by diffusion models.
• Score: 1.7041248235270654
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the empirical success of score-based diffusion models, a complete theoretical understanding of how finite-sample learning, network parameterization, and numerical discretization jointly dictate generative quality remains underdeveloped. Existing sampling analyses often evaluate the generative performance conditional on an oracle score or a pre-specified error threshold. In this work, we establish a unified convergence and generalization framework for score-based diffusion models parameterized by practical ResNet-type architectures. We analyze the generalization and convergence properties from the practical finite-sample, discrete-time learning problem of the score function to the ideal continuous-time, population-level objective. Based on the generalization result of the learning problem of score function, we analyze the sampling process induced by the learned score function and provide an end-to-end total variation distance estimate for the generated terminal distribution. This estimate explicitly decomposes the overall generative error into four interpretable components: the truncation error of the forward process, the reverse-time discretization error, the generalization error incorporating both finite data and forward-time discretization, and the training optimization gap. Our results quantitatively characterize how the training sample size, temporal discretization grids, and optimization accuracy jointly control the final fidelity of samples generated by diffusion models.

Related papers

• Biased Generalization in Diffusion Models [4.602851365305176]
  Generalization in generative modeling is defined as the ability to learn an underlying distribution from a finite dataset and produce novel samples.<n>In practice, training is often stopped at the minimum of the test loss, taken as an operational indicator of generalization.<n>We challenge this viewpoint by identifying a phase of biased generalization during training, in which the model continues to decrease the test loss while favoring samples with anomalously high proximity to training data.
  arXiv  Detail & Related papers  (2026-03-03T19:25:33Z)
• Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching [60.37045080890305]
  We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
  arXiv  Detail & Related papers  (2025-12-01T05:14:25Z)
• Dimension-free Score Matching and Time Bootstrapping for Diffusion Models [19.62665684173391]
  Diffusion models generate samples by estimating the score function of the target distribution at various noise levels.<n>We introduce a martingale-based error decomposition and sharp variance bounds, enabling efficient learning from dependent data.<n>Building on these insights, we propose Bootstrapped Score Matching (BSM), a variance reduction technique that leverages previously learned scores to improve accuracy at higher noise levels.
  arXiv  Detail & Related papers  (2025-02-14T18:32:22Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis [56.442307356162864]
  We study the theoretical aspects of score-based discrete diffusion models under the Continuous Time Markov Chain (CTMC) framework.<n>We introduce a discrete-time sampling algorithm in the general state space $[S]d$ that utilizes score estimators at predefined time points.<n>Our convergence analysis employs a Girsanov-based method and establishes key properties of the discrete score function.
  arXiv  Detail & Related papers  (2024-10-03T09:07:13Z)
• High-dimensional logistic regression with missing data: Imputation, regularization, and universality [7.167672851569787]
  We study high-dimensional, ridge-regularized logistic regression. We provide exact characterizations of both the prediction error and the estimation error.
  arXiv  Detail & Related papers  (2024-10-01T21:41:21Z)
• Aggregation Weighting of Federated Learning via Generalization Bound Estimation [65.8630966842025]
  Federated Learning (FL) typically aggregates client model parameters using a weighting approach determined by sample proportions. We replace the aforementioned weighting method with a new strategy that considers the generalization bounds of each local model.
  arXiv  Detail & Related papers  (2023-11-10T08:50:28Z)
• Improving Adaptive Conformal Prediction Using Self-Supervised Learning [72.2614468437919]
  We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores. We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.
  arXiv  Detail & Related papers  (2023-02-23T18:57:14Z)
• Studying Generalization Through Data Averaging [0.0]
  We study train and test performance, as well as the generalization gap given by the mean of their difference over different data set samples. We predict some aspects about how the generalization gap and model train and test performance vary as a function of SGD noise.
  arXiv  Detail & Related papers  (2022-06-28T00:03:40Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)
• Generalization Error for Linear Regression under Distributed Learning [0.0]
  We consider the setting where the unknowns are distributed over a network of nodes. We present an analytical characterization of the dependence of the generalization error on the partitioning of the unknowns over nodes.
  arXiv  Detail & Related papers  (2020-04-30T08:49:46Z)

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.