On Calibrating Diffusion Probabilistic Models
- URL: http://arxiv.org/abs/2302.10688v3
- Date: Sun, 29 Oct 2023 12:14:29 GMT
- Title: On Calibrating Diffusion Probabilistic Models
- Authors: Tianyu Pang, Cheng Lu, Chao Du, Min Lin, Shuicheng Yan, Zhijie Deng
- Abstract summary: diffusion probabilistic models (DPMs) have achieved promising results in diverse generative tasks.
We propose a simple way for calibrating an arbitrary pretrained DPM, with which the score matching loss can be reduced and the lower bounds of model likelihood can be increased.
Our calibration method is performed only once and the resulting models can be used repeatedly for sampling.
- Score: 78.75538484265292
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, diffusion probabilistic models (DPMs) have achieved promising
results in diverse generative tasks. A typical DPM framework includes a forward
process that gradually diffuses the data distribution and a reverse process
that recovers the data distribution from time-dependent data scores. In this
work, we observe that the stochastic reverse process of data scores is a
martingale, from which concentration bounds and the optional stopping theorem
for data scores can be derived. Then, we discover a simple way for calibrating
an arbitrary pretrained DPM, with which the score matching loss can be reduced
and the lower bounds of model likelihood can consequently be increased. We
provide general calibration guidelines under various model parametrizations.
Our calibration method is performed only once and the resulting models can be
used repeatedly for sampling. We conduct experiments on multiple datasets to
empirically validate our proposal. Our code is at
https://github.com/thudzj/Calibrated-DPMs.
Related papers
- DistPred: A Distribution-Free Probabilistic Inference Method for Regression and Forecasting [14.390842560217743]
We propose a novel approach called DistPred for regression and forecasting tasks.
We transform proper scoring rules that measure the discrepancy between the predicted distribution and the target distribution into a differentiable discrete form.
This allows the model to sample numerous samples in a single forward pass to estimate the potential distribution of the response variable.
arXiv Detail & Related papers (2024-06-17T10:33:00Z) - Contractive Diffusion Probabilistic Models [5.217870815854702]
Diffusion probabilistic models (DPMs) have emerged as a promising technique in generative modeling.
We propose a new criterion -- the contraction property of backward sampling in the design of DPMs, leading to a novel class of contractive DPMs (CDPMs)
We show that CDPM can leverage weights of pretrained DPMs by a simple transformation, and does not need retraining.
arXiv Detail & Related papers (2024-01-23T21:51:51Z) - AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models [103.41269503488546]
Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models with user-provided concepts.
This paper aims to address the challenge of DPM customization when the only available supervision is a differentiable metric defined on the generated contents.
We propose a novel method AdjointDPM, which first generates new samples from diffusion models by solving the corresponding probability-flow ODEs.
It then uses the adjoint sensitivity method to backpropagate the gradients of the loss to the models' parameters.
arXiv Detail & Related papers (2023-07-20T09:06:21Z) - Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps [23.144083737873263]
Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the synthesis of high-quality images.
Previous work has attempted to mitigate this issue by perturbing inputs during training.
We propose a novel sampling method that we propose, without retraining the model.
arXiv Detail & Related papers (2023-05-24T21:39:27Z) - Training Normalizing Flows with the Precision-Recall Divergence [73.92251251511199]
We show that achieving a specified precision-recall trade-off corresponds to minimising -divergences from a family we call the em PR-divergences
We propose a novel generative model that is able to train a normalizing flow to minimise any -divergence, and in particular, achieve a given precision-recall trade-off.
arXiv Detail & Related papers (2023-02-01T17:46:47Z) - Learning from aggregated data with a maximum entropy model [73.63512438583375]
We show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis.
We present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.
arXiv Detail & Related papers (2022-10-05T09:17:27Z) - Pseudo Numerical Methods for Diffusion Models on Manifolds [77.40343577960712]
Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples.
DDPMs require hundreds to thousands of iterations to produce final samples.
We propose pseudo numerical methods for diffusion models (PNDMs)
PNDMs can generate higher quality synthetic images with only 50 steps compared with 1000-step DDIMs (20x speedup)
arXiv Detail & Related papers (2022-02-20T10:37:52Z) - Imputation-Free Learning from Incomplete Observations [73.15386629370111]
We introduce the importance of guided gradient descent (IGSGD) method to train inference from inputs containing missing values without imputation.
We employ reinforcement learning (RL) to adjust the gradients used to train the models via back-propagation.
Our imputation-free predictions outperform the traditional two-step imputation-based predictions using state-of-the-art imputation methods.
arXiv Detail & Related papers (2021-07-05T12:44:39Z) - Improved Denoising Diffusion Probabilistic Models [4.919647298882951]
We show that DDPMs can achieve competitive log-likelihoods while maintaining high sample quality.
We also find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes.
We show that the sample quality and likelihood of these models scale smoothly with model capacity and training compute, making them easily scalable.
arXiv Detail & Related papers (2021-02-18T23:44:17Z)
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.