Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models

by   Fan Bao, et al.

Diffusion probabilistic models (DPMs) are a class of powerful deep generative models (DGMs). Despite their success, the iterative generation process over the full timesteps is much less efficient than other DGMs such as GANs. Thus, the generation performance on a subset of timesteps is crucial, which is greatly influenced by the covariance design in DPMs. In this work, we consider diagonal and full covariances to improve the expressive power of DPMs. We derive the optimal result for such covariances, and then correct it when the mean of DPMs is imperfect. Both the optimal and the corrected ones can be decomposed into terms of conditional expectations over functions of noise. Building upon it, we propose to estimate the optimal covariance and its correction given imperfect mean by learning these conditional expectations. Our method can be applied to DPMs with both discrete and continuous timesteps. We consider the diagonal covariance in our implementation for computational efficiency. For an efficient practical implementation, we adopt a parameter sharing scheme and a two-stage training process. Empirically, our method outperforms a wide variety of covariance design on likelihood results, and improves the sample quality especially on a small number of timesteps.


page 26

page 27

page 28

page 29

page 30


Few-Shot Diffusion Models

Denoising diffusion probabilistic models (DDPM) are powerful hierarchica...

Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models

Diffusion probabilistic models (DPMs) represent a class of powerful gene...

DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation

Generating novel molecules with optimal properties is a crucial step in ...

Symbolic Music Generation with Diffusion Models

Score-based generative models and diffusion probabilistic models have be...

Optimal change point detection in Gaussian processes

We study the problem of detecting a change in the mean of one-dimensiona...

Noise Estimation for Generative Diffusion Models

Generative diffusion models have emerged as leading models in speech and...