Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs

• URL: http://arxiv.org/abs/2305.03935v4
• Date: Sat, 6 Apr 2024 07:01:53 GMT
• Title: Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
• Authors: Kaiwen Zheng, Cheng Lu, Jianfei Chen, Jun Zhu,
• Abstract summary: We propose several improved techniques for maximum likelihood estimation for diffusion ODEs. For training, we propose velocity parameterization and explore variance reduction techniques for faster convergence. For evaluation, we propose a novel training-free truncated-normal dequantization to fill the training-evaluation gap commonly existing in diffusion ODEs.
• Score: 21.08236758778604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models have exhibited excellent performance in various domains. The probability flow ordinary differential equation (ODE) of diffusion models (i.e., diffusion ODEs) is a particular case of continuous normalizing flows (CNFs), which enables deterministic inference and exact likelihood evaluation. However, the likelihood estimation results by diffusion ODEs are still far from those of the state-of-the-art likelihood-based generative models. In this work, we propose several improved techniques for maximum likelihood estimation for diffusion ODEs, including both training and evaluation perspectives. For training, we propose velocity parameterization and explore variance reduction techniques for faster convergence. We also derive an error-bounded high-order flow matching objective for finetuning, which improves the ODE likelihood and smooths its trajectory. For evaluation, we propose a novel training-free truncated-normal dequantization to fill the training-evaluation gap commonly existing in diffusion ODEs. Building upon these techniques, we achieve state-of-the-art likelihood estimation results on image datasets (2.56 on CIFAR-10, 3.43/3.69 on ImageNet-32) without variational dequantization or data augmentation, and 2.42 on CIFAR-10 with data augmentation. Code is available at \url{https://github.com/thu-ml/i-DODE}.

Related papers

• Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling [2.1779479916071067]
  We introduce a novel framework that enhances diffusion models by supporting a broader range of forward processes. We also propose a novel parameterization technique for learning the forward process. Results underscore NFDM's versatility and its potential for a wide range of applications.
  arXiv  Detail & Related papers  (2024-04-19T15:10:54Z)
• Guided Diffusion from Self-Supervised Diffusion Features [49.78673164423208]
  Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or pretraining. We propose a framework to extract guidance from, and specifically for, diffusion models.
  arXiv  Detail & Related papers  (2023-12-14T11:19:11Z)
• Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations [6.2284442126065525]
  We study the problem mathematically for two limiting scenarios: the zero diffusion (ODE) case and the large diffusion case. Our findings indicate that when the perturbation occurs at the end of the generative process, the ODE model outperforms the SDE model with a large diffusion coefficient.
  arXiv  Detail & Related papers  (2023-06-03T09:27:15Z)
• The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation [42.48819460873482]
  Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly, without task-specific architectures and loss functions.
  arXiv  Detail & Related papers  (2023-06-02T21:26:20Z)
• A Geometric Perspective on Diffusion Models [57.27857591493788]
  We inspect the ODE-based sampling of a popular variance-exploding SDE. We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
  arXiv  Detail & Related papers  (2023-05-31T15:33:16Z)
• Training Diffusion Models with Reinforcement Learning [82.29328477109826]
  Diffusion models are trained with an approximation to the log-likelihood objective. In this paper, we investigate reinforcement learning methods for directly optimizing diffusion models for downstream objectives. We describe how posing denoising as a multi-step decision-making problem enables a class of policy gradient algorithms.
  arXiv  Detail & Related papers  (2023-05-22T17:57:41Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• Stable Target Field for Reduced Variance Score Estimation in Diffusion Models [5.9115407007859755]
  Diffusion models generate samples by reversing a fixed forward diffusion process. We argue that the source of such variance lies in the handling of intermediate noise-variance scales. We propose to remedy the problem by incorporating a reference batch which we use to calculate weighted conditional scores as more stable training targets.
  arXiv  Detail & Related papers  (2023-02-01T18:57:01Z)
• How Much is Enough? A Study on Diffusion Times in Score-based Generative Models [76.76860707897413]
  Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution. We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
  arXiv  Detail & Related papers  (2022-06-10T15:09:46Z)
• A Variational Perspective on Diffusion-Based Generative Models and Score Matching [8.93483643820767]
  We derive a variational framework for likelihood estimation for continuous-time generative diffusion. We show that minimizing the score-matching loss is equivalent to maximizing a lower bound of the likelihood of the plug-in reverse SDE.
  arXiv  Detail & Related papers  (2021-06-05T05:50:36Z)
• Stochasticity in Neural ODEs: An Empirical Study [68.8204255655161]
  Regularization of neural networks (e.g. dropout) is a widespread technique in deep learning that allows for better generalization. We show that data augmentation during the training improves the performance of both deterministic and versions of the same model. However, the improvements obtained by the data augmentation completely eliminate the empirical regularization gains, making the performance of neural ODE and neural SDE negligible.
  arXiv  Detail & Related papers  (2020-02-22T22:12:56Z)

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.