REVIEW 5 cited by
Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. In these applications, conditional diffusion models incorporate various conditional information, such as prompt input, to guide the sample generation towards desired properties. Despite the empirical success, theory of conditional diffusion models is largely missing. This paper bridges this gap by presenting a sharp statistical theory of distribution estimation using conditional diffusion models. Our analysis yields a sample complexity bound that adapts to the smoothness of the data distribution and matches the minimax lower bound. The key to our theoretical development lies in an approximation result for the conditional score function, which relies on a novel diffused Taylor approximation technique. Moreover, we demonstrate the utility of our statistical theory in elucidating the performance of conditional diffusion models across diverse applications, including model-based transition kernel estimation in reinforcement learning, solving inverse problems, and reward conditioned sample generation.
Forward citations
Cited by 5 Pith papers
-
Minimax Optimal Rates for Regression on Manifolds and Distributions
Minimax rates for conditional distribution estimation on manifolds are established, with matching upper bounds from a hybrid wavelet and manifold estimator.
-
Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations
Two-stage conditional generation that samples a low-dimensional sufficient representation from the label and reconstructs data from unlabeled samples achieves convergence rates depending on the representation dimensio...
-
Provable Diffusion Posterior Sampling for Bayesian Inversion
A diffusion posterior sampler using Monte Carlo Langevin score estimation and warm start is proven to converge in Wasserstein-2 distance under semi-log-concavity and sub-Gaussian assumptions, and outperforms DPS/TV on...
-
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
A SVD-based, coordinate-wise DDIM sampler is claimed to asymptotically sample from the posterior for noisy linear inverse problems, but the proof's posterior identification step does not follow from the stated updates.
-
Non-asymptotic convergence bound of conditional diffusion models
CARD's generated conditional distribution is shown to converge in Wasserstein distance to the true conditional distribution, with a separate score-estimation error bound controlled by network resolution and distributi...
Discussion (0). Sign in to comment.