Generative Lines Matching Models

• URL: http://arxiv.org/abs/2412.06403v1
• Date: Mon, 09 Dec 2024 11:33:38 GMT
• Title: Generative Lines Matching Models
• Authors: Ori Matityahu, Raanan Fattal,
• Abstract summary: We propose a new probability flow model, which matches globally straight lines interpolating the two distributions. We demonstrate that the flow fields produced by the LMM exhibit notable temporal consistency, resulting in trajectories with excellent straightness scores. Overall, the LMM achieves state-of-the-art FID scores with minimal NFEs on established benchmark datasets.
• Score: 2.6089354079273512
• License:
• Abstract: In this paper we identify the source of a singularity in the training loss of key denoising models, that causes the denoiser's predictions to collapse towards the mean of the source or target distributions. This degeneracy creates false basins of attraction, distorting the denoising trajectories and ultimately increasing the number of steps required to sample these models. We circumvent this artifact by leveraging the deterministic ODE-based samplers, offered by certain denoising diffusion and score-matching models, which establish a well-defined change-of-variables between the source and target distributions. Given this correspondence, we propose a new probability flow model, the Lines Matching Model (LMM), which matches globally straight lines interpolating the two distributions. We demonstrate that the flow fields produced by the LMM exhibit notable temporal consistency, resulting in trajectories with excellent straightness scores. Beyond its sampling efficiency, the LMM formulation allows us to enhance the fidelity of the generated samples by integrating domain-specific reconstruction and adversarial losses, and by optimizing its training for the sampling procedure used. Overall, the LMM achieves state-of-the-art FID scores with minimal NFEs on established benchmark datasets: 1.57/1.39 (NFE=1/2) on CIFAR-10, 1.47/1.17 on ImageNet 64x64, and 2.68/1.54 on AFHQ 64x64. Finally, we provide a theoretical analysis showing that the use of optimal transport to relate the two distributions suffers from a curse of dimensionality, where the pairing set size (mini-batch) must scale exponentially with the signal dimension.

Related papers

• Dimension-free Score Matching and Time Bootstrapping for Diffusion Models [11.743167854433306]
  Diffusion models generate samples by estimating the score function of the target distribution at various noise levels. In this work, we establish the first (nearly) dimension-free sample bounds complexity for learning these score functions. A key aspect of our analysis is the use of a single function approximator to jointly estimate scores across noise levels.
  arXiv  Detail & Related papers  (2025-02-14T18:32:22Z)
• Direct Distributional Optimization for Provable Alignment of Diffusion Models [39.048284342436666]
  We introduce a novel alignment method for diffusion models from distribution optimization perspectives. We first formulate the problem as a generic regularized loss minimization over probability distributions. We enable sampling from the learned distribution by approximating its score function via Doob's $h$-transform technique.
  arXiv  Detail & Related papers  (2025-02-05T07:35:15Z)
• 2-Rectifications are Enough for Straight Flows: A Theoretical Insight into Wasserstein Convergence [54.580605276017096]
  We provide the first theoretical analysis of the Wasserstein distance between the sampling distribution of Rectified Flow and the target distribution. We show that for a rectified flow from a Gaussian to any general target distribution with finite first moment, two rectifications are sufficient to achieve a straight flow.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional general score-mismatched diffusion samplers. We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions. This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance. Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• The Score-Difference Flow for Implicit Generative Modeling [1.1929584800629673]
  Implicit generative modeling aims to produce samples of synthetic data matching a target data distribution. Recent work has approached the IGM problem from the perspective of pushing synthetic source data toward the target distribution. We present the score difference between arbitrary target and source distributions as a flow that optimally reduces the Kullback-Leibler divergence between them.
  arXiv  Detail & Related papers  (2023-04-25T15:21:12Z)
• Information Theoretic Structured Generative Modeling [13.117829542251188]
  A novel generative model framework called the structured generative model (SGM) is proposed that makes straightforward optimization possible. The implementation employs a single neural network driven by an orthonormal input to a single white noise source adapted to learn an infinite Gaussian mixture model. Preliminary results show that SGM significantly improves MINE estimation in terms of data efficiency and variance, conventional and variational Gaussian mixture models, as well as for training adversarial networks.
  arXiv  Detail & Related papers  (2021-10-12T07:44:18Z)
• Achieving Efficiency in Black Box Simulation of Distribution Tails with Self-structuring Importance Samplers [1.6114012813668934]
  The paper presents a novel Importance Sampling (IS) scheme for estimating distribution of performance measures modeled with a rich set of tools such as linear programs, integer linear programs, piecewise linear/quadratic objectives, feature maps specified with deep neural networks, etc.
  arXiv  Detail & Related papers  (2021-02-14T03:37:22Z)
• Learning to Match Distributions for Domain Adaptation [116.14838935146004]
  This paper proposes Learning to Match (L2M) to automatically learn the cross-domain distribution matching. L2M reduces the inductive bias by using a meta-network to learn the distribution matching loss in a data-driven way. Experiments on public datasets substantiate the superiority of L2M over SOTA methods.
  arXiv  Detail & Related papers  (2020-07-17T03:26:13Z)
• Generative Modeling with Denoising Auto-Encoders and Langevin Sampling [88.83704353627554]
  We show that both DAE and DSM provide estimates of the score of the smoothed population density. We then apply our results to the homotopy method of arXiv:1907.05600 and provide theoretical justification for its empirical success.
  arXiv  Detail & Related papers  (2020-01-31T23:50:03Z)

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.