Energy-based generator matching: A neural sampler for general state space

• URL: http://arxiv.org/abs/2505.19646v2
• Date: Tue, 27 May 2025 05:18:11 GMT
• Title: Energy-based generator matching: A neural sampler for general state space
• Authors: Dongyeop Woo, Minsu Kim, Minkyu Kim, Kiyoung Seong, Sungsoo Ahn,
• Abstract summary: We propose Energy-based generator matching (EGM) to train generative models from energy functions in the absence of data.<n>EGM enables training of arbitrary continuous-time Markov processes, e.g., diffusion, flow, and jump, and can generate data from continuous, discrete, and a mixture of two modalities.
• Score: 26.45926098524023
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose Energy-based generator matching (EGM), a modality-agnostic approach to train generative models from energy functions in the absence of data. Extending the recently proposed generator matching, EGM enables training of arbitrary continuous-time Markov processes, e.g., diffusion, flow, and jump, and can generate data from continuous, discrete, and a mixture of two modalities. To this end, we propose estimating the generator matching loss using self-normalized importance sampling with an additional bootstrapping trick to reduce variance in the importance weight. We validate EGM on both discrete and multimodal tasks up to 100 and 20 dimensions, respectively.

Related papers

• Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling [4.395339671282145]
  Energy-based models (EBMs) map noise and data distributions by matching flows or scores.<n>We propose Energy Matching, a framework that endows flow-based approaches with the flexibility of EBMs.<n>Our method substantially outperforms existing EBMs on CIFAR-10 and ImageNet generation in terms of fidelity.
  arXiv  Detail & Related papers  (2025-04-14T18:10:58Z)
• Scalable Equilibrium Sampling with Sequential Boltzmann Generators [60.00515282300297]
  We extend the Boltzmann generator framework and introduce Sequential Boltzmann generators with two key improvements.<n>The first is a highly efficient non-equivariant Transformer-based normalizing flow operating directly on all-atom Cartesian coordinates.<n>We demonstrate the first equilibrium sampling in Cartesian coordinates of tri, tetra, and hexapeptides that were so far intractable for prior Boltzmann generators.
  arXiv  Detail & Related papers  (2025-02-25T18:59:13Z)
• Iterated Denoising Energy Matching for Sampling from Boltzmann Densities [109.23137009609519]
  Iterated Denoising Energy Matching (iDEM) iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our matching objective. We show that the proposed approach achieves state-of-the-art performance on all metrics and trains $2-5times$ faster.
  arXiv  Detail & Related papers  (2024-02-09T01:11:23Z)
• Energy based diffusion generator for efficient sampling of Boltzmann distributions [11.855642710689704]
  Energy-Based Diffusion Generator (EDG) is a novel approach that integrates ideas from variational autoencoders and diffusion models. EDG is simulation-free, eliminating the need to solve ordinary or differential equations during training.
  arXiv  Detail & Related papers  (2024-01-04T06:03:46Z)
• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks [0.0]
  Generative Adversarial Networks (GANs) have shown immense potential in fields such as text and image generation. Here we quantitatively test this approach by applying it to a prototypical process on a lattice. Importantly, the discreteness of the model is retained despite the noise.
  arXiv  Detail & Related papers  (2023-05-25T10:41:02Z)
• Learning Probabilistic Models from Generator Latent Spaces with Hat EBM [81.35199221254763]
  This work proposes a method for using any generator network as the foundation of an Energy-Based Model (EBM) Experiments show strong performance of the proposed method on (1) unconditional ImageNet synthesis at 128x128 resolution, (2) refining the output of existing generators, and (3) learning EBMs that incorporate non-probabilistic generators.
  arXiv  Detail & Related papers  (2022-10-29T03:55:34Z)
• Towards a scalable discrete quantum generative adversarial neural network [8.134122612459633]
  We introduce a fully quantum generative adversarial network intended for use with binary data. In particular, we incorporate noise reuploading in the generator, auxiliary qubits in the discriminator to enhance expressivity. We empirically demonstrate the expressive power of our model on both synthetic data and low energy states of an Ising model.
  arXiv  Detail & Related papers  (2022-09-28T10:42:38Z)
• An Energy-Based Prior for Generative Saliency [62.79775297611203]
  We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution. With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction. Experimental results show that our generative saliency model with an energy-based prior can achieve not only accurate saliency predictions but also reliable uncertainty maps consistent with human perception.
  arXiv  Detail & Related papers  (2022-04-19T10:51:00Z)
• Continual Learning with Fully Probabilistic Models [70.3497683558609]
  We present an approach for continual learning based on fully probabilistic (or generative) models of machine learning. We propose a pseudo-rehearsal approach using a Gaussian Mixture Model (GMM) instance for both generator and classifier functionalities. We show that GMR achieves state-of-the-art performance on common class-incremental learning problems at very competitive time and memory complexity.
  arXiv  Detail & Related papers  (2021-04-19T12:26:26Z)
• Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling [106.68533003806276]
  We show that sampling in latent space can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score. We show that Discriminator Driven Latent Sampling(DDLS) is highly efficient compared to previous methods which work in the high-dimensional pixel space.
  arXiv  Detail & Related papers  (2020-03-12T23:33:50Z)

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.