REVIEW 7 cited by
Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
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
Diffusion probabilistic models (DPMs) represent a class of powerful generative models. Despite their success, the inference of DPMs is expensive since it generally needs to iterate over thousands of timesteps. A key problem in the inference is to estimate the variance in each timestep of the reverse process. In this work, we present a surprising result that both the optimal reverse variance and the corresponding optimal KL divergence of a DPM have analytic forms w.r.t. its score function. Building upon it, we propose Analytic-DPM, a training-free inference framework that estimates the analytic forms of the variance and KL divergence using the Monte Carlo method and a pretrained score-based model. Further, to correct the potential bias caused by the score-based model, we derive both lower and upper bounds of the optimal variance and clip the estimate for a better result. Empirically, our analytic-DPM improves the log-likelihood of various DPMs, produces high-quality samples, and meanwhile enjoys a 20x to 80x speed up.
Forward citations
Cited by 7 Pith papers
-
Amortized Moment Matching for Visual Generation
Amortized Fréchet Distance uses neural nets to match conditional means and covariances, yielding stronger one-step visual generators than explicit FD-loss or multi-step teachers.
-
M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation
M2IO-R1 uses GRPO reinforcement learning to train a 3B model that selects and places retrieved images into generated text answers, improving MRAMG quality on several benchmarks.
-
FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment
Aligning the L2-norm statistics of noise predictions during diffusion sampling improves domain adaptation for dense prediction, with a source-free version guided by high-confidence regions.
-
Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
The diffusion Fisher matrix of a Gaussian-perturbed distribution is expressed in the span of data outer products, enabling two faster approximation algorithms for trace and matrix-vector access.
-
Straighten Viscous Rectified Flow via Noise Optimization
VRFNO claims state-of-the-art one- and few-step image generation by straightening rectified flow trajectories, but its sampler relies on real images from the dataset.
-
DiffIER: Optimizing Diffusion Models with Iterative Error Reduction
DiffIER claims that iteratively minimizing the distance between a diffusion model's predicted noise and a random Gaussian sample at each inference step improves generation quality.
-
Diffusion Models for Time Series Forecasting: A Survey
A survey classifies diffusion-based time series forecasting models into a two-axis taxonomy by conditioning source and integration method.
Discussion (0). Continue with ORCID to comment.