cs.LGNov 1, 2026

Finite-Time Online Sample Complexity for Conditional Diffusion Models

Authors: Mudit Gaur, Prashant Trivedi, Sasidhar Kunapuli, Amrit Singh Bedi, Vaneet Aggarwal

Organizations: Department of Electrical and Computer Engineering, Ohio State Univeristy · Department of Computer Science and Information Systems, BITS Pilani · Department of Computer Science, University of Central Florida · Edwardson School of Industrial Engineering, Purdue University

Abstract

We study the finite-time training and sampling error of conditional diffusion models trained by online stochastic-gradient denoising score matching. Rather than assuming access to an exact empirical or population risk minimizer, we analyze the score network produced after a finite number of stochastic-gradient updates under an explicit localized Polyak--Łojasiewicz (PL) condition, stochastic-gradient regularity, and a trajectory-containment assumption. Our analysis separates the network approximation complexity from the online training-sample budget and propagates both errors through the reverse diffusion process. Under anisotropic smoothness, a joint intrinsic-dimensional structure for the data and conditioning variables, sub-exponential tails, and explicit approximation-class compatibility, we obtain a conditional score approximation error of order

O~ ⁣(M−ηapp),ηapp=2αx2αx+dx′+(αx/αy)dy′,\widetilde{\mathcal O}\!\left(M^{-η_{\mathrm{app}}}\right), \qquad η_{\mathrm{app}} = \frac{2α_x} {2α_x+d_x'+(α_x/α_y)d_y'},

where MM denotes the approximation complexity, dx′d_x' and dy′d_y' are the intrinsic response and conditioning dimensions, and αx,αyα_x,α_y are their corresponding smoothness exponents. For N=RBN=RB online denoising samples used by SGD, the finite-time optimization error is controlled explicitly in terms of the PL, smoothness, gradient-noise, and initialization constants. Combining these ingredients with reverse-process stability yields a total-variation bound that decomposes into terminal-initialization, time-discretization, approximation/localization, and finite-time optimization errors.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Finite-Sample Guarantees for Fully Discrete Conditional Diffusion Models

    Oct 9, 2026Qiuyun ZhuConditional Diffusion ModelsDiffusion Sampling

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

    Jul 25, 2026Jinshu Huang, Yiming Jiang, Chunlin WuDiffusion Model SamplingScore-Based Generative Modeling

  3. Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors

    Jun 4, 2026Naïl B. Khelifa, Richard E. Turner, Ramji VenkataramananScore MatchingHodge Decomposition