Designing a Conditional Prior Distribution for Flow-Based Generative Models
- URL: http://arxiv.org/abs/2502.09611v1
- Date: Thu, 13 Feb 2025 18:58:15 GMT
- Title: Designing a Conditional Prior Distribution for Flow-Based Generative Models
- Authors: Noam Issachar, Mohammad Salama, Raanan Fattal, Sagie Benaim,
- Abstract summary: Flow-basedgenerative models have recently shown impressive performance for conditional generation tasks.
In this work, we tap into a non-utilized property of conditional flow-based models: the ability to design a non-trivial prior distribution.
We utilize the flow matching formulation to map samples from a parametric distribution centered around this point to the conditional target distribution.
- Score: 16.729797131896138
- License:
- Abstract: Flow-based generative models have recently shown impressive performance for conditional generation tasks, such as text-to-image generation. However, current methods transform a general unimodal noise distribution to a specific mode of the target data distribution. As such, every point in the initial source distribution can be mapped to every point in the target distribution, resulting in long average paths. To this end, in this work, we tap into a non-utilized property of conditional flow-based models: the ability to design a non-trivial prior distribution. Given an input condition, such as a text prompt, we first map it to a point lying in data space, representing an ``average" data point with the minimal average distance to all data points of the same conditional mode (e.g., class). We then utilize the flow matching formulation to map samples from a parametric distribution centered around this point to the conditional target distribution. Experimentally, our method significantly improves training times and generation efficiency (FID, KID and CLIP alignment scores) compared to baselines, producing high quality samples using fewer sampling steps.
Related papers
- Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo [10.948453531321032]
We introduce a Sequential Monte Carlo algorithm that generates unbiasedly from a target distribution.
We validate our approach on low-dimensional distributions, controlled images and text generations.
arXiv Detail & Related papers (2025-02-10T00:27:54Z) - Distributional Diffusion Models with Scoring Rules [83.38210785728994]
Diffusion models generate high-quality synthetic data.
generating high-quality outputs requires many discretization steps.
We propose to accomplish sample generation by learning the posterior em distribution of clean data samples.
arXiv Detail & Related papers (2025-02-04T16:59:03Z) - 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) - Distributed Markov Chain Monte Carlo Sampling based on the Alternating
Direction Method of Multipliers [143.6249073384419]
In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers.
We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art.
In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
arXiv Detail & Related papers (2024-01-29T02:08:40Z) - Probabilistic Matching of Real and Generated Data Statistics in Generative Adversarial Networks [0.6906005491572401]
We propose a method to ensure that the distributions of certain generated data statistics coincide with the respective distributions of the real data.
We evaluate the method on a synthetic dataset and a real-world dataset and demonstrate improved performance of our approach.
arXiv Detail & Related papers (2023-06-19T14:03:27Z) - Continuous and Distribution-free Probabilistic Wind Power Forecasting: A
Conditional Normalizing Flow Approach [1.684864188596015]
We present a data-driven approach for probabilistic wind power forecasting based on conditional normalizing flow (CNF)
In contrast with the existing, this approach is distribution-free (as for non-parametric and quantile-based approaches) and can directly yield continuous probability densities.
arXiv Detail & Related papers (2022-06-06T08:48:58Z) - VQ-Flows: Vector Quantized Local Normalizing Flows [2.7998963147546148]
We introduce a novel statistical framework for learning a mixture of local normalizing flows as "chart maps" over a data manifold.
Our framework augments the expressivity of recent approaches while preserving the signature property of normalizing flows, that they admit exact density evaluation.
arXiv Detail & Related papers (2022-03-22T09:22:18Z) - Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
We take a two-step approach by first modeling the probability distribution and then sampling from that model.
We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
arXiv Detail & Related papers (2021-10-20T12:25:22Z) - Improving Generative Adversarial Networks with Local Coordinate Coding [150.24880482480455]
Generative adversarial networks (GANs) have shown remarkable success in generating realistic data from some predefined prior distribution.
In practice, semantic information might be represented by some latent distribution learned from data.
We propose an LCCGAN model with local coordinate coding (LCC) to improve the performance of generating data.
arXiv Detail & Related papers (2020-07-28T09:17:50Z) - Pre-training Is (Almost) All You Need: An Application to Commonsense
Reasoning [61.32992639292889]
Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks.
We introduce a new scoring method that casts a plausibility ranking task in a full-text format.
We show that our method provides a much more stable training phase across random restarts.
arXiv Detail & Related papers (2020-04-29T10:54:40Z)
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.