Generative Modeling with Flow-Guided Density Ratio Learning

• URL: http://arxiv.org/abs/2303.03714v3
• Date: Wed, 5 Jun 2024 03:00:33 GMT
• Title: Generative Modeling with Flow-Guided Density Ratio Learning
• Authors: Alvin Heng, Abdul Fatir Ansari, Harold Soh,
• Abstract summary: Flow-Guided Density Ratio Learning (FDRL) is a simple and scalable approach to generative modeling. We show that FDRL can generate images of dimensions as high as $128times128$, as well as outperform existing gradient flow baselines on quantitative benchmarks.
• Score: 12.192867460641835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Flow-Guided Density Ratio Learning (FDRL), a simple and scalable approach to generative modeling which builds on the stale (time-independent) approximation of the gradient flow of entropy-regularized f-divergences introduced in recent work. Specifically, the intractable time-dependent density ratio is approximated by a stale estimator given by a GAN discriminator. This is sufficient in the case of sample refinement, where the source and target distributions of the flow are close to each other. However, this assumption is invalid for generation and a naive application of the stale estimator fails due to the large chasm between the two distributions. FDRL proposes to train a density ratio estimator such that it learns from progressively improving samples during the training process. We show that this simple method alleviates the density chasm problem, allowing FDRL to generate images of dimensions as high as $128\times128$, as well as outperform existing gradient flow baselines on quantitative benchmarks. We also show the flexibility of FDRL with two use cases. First, unconditional FDRL can be easily composed with external classifiers to perform class-conditional generation. Second, FDRL can be directly applied to unpaired image-to-image translation with no modifications needed to the framework. Our code is publicly available at ttps://github.com/clear-nus/fdrl.

Related papers

• Rectified Diffusion Guidance for Conditional Generation [62.00207951161297]
  We revisit the theory behind CFG and rigorously confirm that the improper configuration of the combination coefficients (i.e., the widely used summing-to-one version) brings about expectation shift of the generative distribution. We propose ReCFG with a relaxation on the guidance coefficients such that denoising with ReCFG strictly aligns with the diffusion theory. That way the rectified coefficients can be readily pre-computed via traversing the observed data, leaving the sampling speed barely affected.
  arXiv  Detail & Related papers  (2024-10-24T13:41:32Z)
• Straightness of Rectified Flow: A Theoretical Insight into Wasserstein Convergence [54.580605276017096]
  Rectified Flow (RF) aims to learn straight flow trajectories from noise to data using a sequence of convex optimization problems. RF theoretically straightens the trajectory through successive rectifications, reducing the number of evaluations function (NFEs) while sampling. We provide the first theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow [65.51671121528858]
  Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path. We propose Rectified Diffusion, which generalizes the design space and application scope of rectification to encompass the broader category of diffusion models.
  arXiv  Detail & Related papers  (2024-10-09T17:43:38Z)
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding [84.3224556294803]
  Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. We aim to optimize downstream reward functions while preserving the naturalness of these design spaces. Our algorithm integrates soft value functions, which looks ahead to how intermediate noisy states lead to high rewards in the future.
  arXiv  Detail & Related papers  (2024-08-15T16:47:59Z)
• FedUV: Uniformity and Variance for Heterogeneous Federated Learning [5.9330433627374815]
  Federated learning is a promising framework to train neural networks with widely distributed data. Recent work has shown this is due to the final layer of the network being most prone to local bias. We investigate the training dynamics of the classifier by applying SVD to the weights motivated by the observation that freezing weights results in constant singular values.
  arXiv  Detail & Related papers  (2024-02-27T15:53:15Z)
• Adversarial Likelihood Estimation With One-Way Flows [44.684952377918904]
  Generative Adversarial Networks (GANs) can produce high-quality samples, but do not provide an estimate of the probability density around the samples. We show that our method converges faster, produces comparable sample quality to GANs with similar architecture, successfully avoids over-fitting to commonly used datasets and produces smooth low-dimensional latent representations of the training data.
  arXiv  Detail & Related papers  (2023-07-19T10:26:29Z)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models [49.81937966106691]
  We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models. In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
  arXiv  Detail & Related papers  (2023-06-15T16:30:08Z)
• Subspace Diffusion Generative Models [4.310834990284412]
  Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We restrict the diffusion via projections onto subspaces as the data distribution evolves toward noise. Our framework is fully compatible with continuous-time diffusion and retains its flexible capabilities.
  arXiv  Detail & Related papers  (2022-05-03T13:43:47Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)

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.