Learned Reference-based Diffusion Sampling for multi-modal distributions
- URL: http://arxiv.org/abs/2410.19449v1
- Date: Fri, 25 Oct 2024 10:23:34 GMT
- Title: Learned Reference-based Diffusion Sampling for multi-modal distributions
- Authors: Maxence Noble, Louis Grenioux, Marylou GabriƩ, Alain Oliviero Durmus,
- Abstract summary: We introduce Learned Reference-based Diffusion Sampler (LRDS), a methodology specifically designed to leverage prior knowledge on the location of the target modes.
LRDS proceeds in two steps by learning a reference diffusion model on samples located in high-density space regions.
We experimentally demonstrate that LRDS best exploits prior knowledge on the target distribution compared to competing algorithms on a variety of challenging distributions.
- Score: 2.1383136715042417
- License:
- Abstract: Over the past few years, several approaches utilizing score-based diffusion have been proposed to sample from probability distributions, that is without having access to exact samples and relying solely on evaluations of unnormalized densities. The resulting samplers approximate the time-reversal of a noising diffusion process, bridging the target distribution to an easy-to-sample base distribution. In practice, the performance of these methods heavily depends on key hyperparameters that require ground truth samples to be accurately tuned. Our work aims to highlight and address this fundamental issue, focusing in particular on multi-modal distributions, which pose significant challenges for existing sampling methods. Building on existing approaches, we introduce Learned Reference-based Diffusion Sampler (LRDS), a methodology specifically designed to leverage prior knowledge on the location of the target modes in order to bypass the obstacle of hyperparameter tuning. LRDS proceeds in two steps by (i) learning a reference diffusion model on samples located in high-density space regions and tailored for multimodality, and (ii) using this reference model to foster the training of a diffusion-based sampler. We experimentally demonstrate that LRDS best exploits prior knowledge on the target distribution compared to competing algorithms on a variety of challenging distributions.
Related papers
- 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) - Annealing Flow Generative Model Towards Sampling High-Dimensional and Multi-Modal Distributions [6.992239210938067]
Annealing Flow is a continuous normalizing flow based approach designed to sample from high dimensional and multimodal distributions.
AF ensures effective and balanced mode exploration, achieves linear complexity in sample size and dimensions, and circumvents inefficient mixing times.
arXiv Detail & Related papers (2024-09-30T17:48:22Z) - A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization [7.378582040635655]
Current deep learning approaches rely on generative models that yield exact sample likelihoods.
This work introduces a method that lifts this restriction and opens the possibility to employ highly expressive latent variable models.
We experimentally validate our approach in data-free Combinatorial Optimization and demonstrate that our method achieves a new state-of-the-art on a wide range of benchmark problems.
arXiv Detail & Related papers (2024-06-03T17:55:02Z) - Improved off-policy training of diffusion samplers [93.66433483772055]
We study the problem of training diffusion models to sample from a distribution with an unnormalized density or energy function.
We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods.
Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work.
arXiv Detail & Related papers (2024-02-07T18:51:49Z) - 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) - Improved sampling via learned diffusions [8.916420423563478]
Recently, a series of papers proposed deep learning-based approaches to sample from target distributions using controlled diffusion processes.
We identify these approaches as special cases of a generalized Schr"odinger bridge problem.
We propose a variational formulation based on divergences between path space measures of time-reversed diffusion processes.
arXiv Detail & Related papers (2023-07-03T17:58:26Z) - Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps.
We introduce a novel approach that tackles the problem by matching implicit and explicit factors.
We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
arXiv Detail & Related papers (2023-06-21T18:49:22Z) - Fast Inference in Denoising Diffusion Models via MMD Finetuning [23.779985842891705]
We present MMD-DDM, a novel method for fast sampling of diffusion models.
Our approach is based on the idea of using the Maximum Mean Discrepancy (MMD) to finetune the learned distribution with a given budget of timesteps.
Our findings show that the proposed method is able to produce high-quality samples in a fraction of the time required by widely-used diffusion models.
arXiv Detail & Related papers (2023-01-19T09:48:07Z) - Robust Calibration with Multi-domain Temperature Scaling [86.07299013396059]
We develop a systematic calibration model to handle distribution shifts by leveraging data from multiple domains.
Our proposed method -- multi-domain temperature scaling -- uses the robustness in the domains to improve calibration under distribution shift.
arXiv Detail & Related papers (2022-06-06T17:32:12Z) - 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.