A Diffusive Classification Loss for Learning Energy-based Generative Models

• URL: http://arxiv.org/abs/2601.21025v2
• Date: Sat, 31 Jan 2026 02:29:42 GMT
• Title: A Diffusive Classification Loss for Learning Energy-based Generative Models
• Authors: RuiKang OuYang, Louis Grenioux, José Miguel Hernández-Lobato,
• Abstract summary: We introduce the Diffusive Classification (DiffCLF) objective, a simple method that avoids blindness while remaining computationally efficient.<n>We validate the effectiveness of DiffCLF by comparing the estimated energies against ground truth in analytical Gaussian mixture cases.<n>Our results show that DiffCLF enables EBMs with higher fidelity and broader applicability than existing approaches.
• Score: 27.078167178968076
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Score-based generative models have recently achieved remarkable success. While they are usually parameterized by the score, an alternative way is to use a series of time-dependent energy-based models (EBMs), where the score is obtained from the negative input-gradient of the energy. Crucially, EBMs can be leveraged not only for generation, but also for tasks such as compositional sampling or building Boltzmann Generators via Monte Carlo methods. However, training EBMs remains challenging. Direct maximum likelihood is computationally prohibitive due to the need for nested sampling, while score matching, though efficient, suffers from mode blindness. To address these issues, we introduce the Diffusive Classification (DiffCLF) objective, a simple method that avoids blindness while remaining computationally efficient. DiffCLF reframes EBM learning as a supervised classification problem across noise levels, and can be seamlessly combined with standard score-based objectives. We validate the effectiveness of DiffCLF by comparing the estimated energies against ground truth in analytical Gaussian mixture cases, and by applying the trained models to tasks such as model composition and Boltzmann Generator sampling. Our results show that DiffCLF enables EBMs with higher fidelity and broader applicability than existing approaches.

Related papers

• FALCON: Few-step Accurate Likelihoods for Continuous Flows [78.37361800856583]
  We propose Few-step Accurate Likelihoods for Continuous Flows (FALCON), which allows for few-step sampling with a likelihood accurate enough for importance sampling applications.<n>We show FALCON outperforms state-of-the-art normalizing flow models for molecular Boltzmann sampling and is two orders of magnitude faster than the equivalently performing CNF model.
  arXiv  Detail & Related papers  (2025-12-10T18:47:25Z)
• BoltzNCE: Learning Likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation [1.2874523233023452]
  Efficient sampling from the Boltzmann distribution is a key challenge for modeling complex physical systems such as molecules.<n>We train an energy-based model (EBM) to approximate likelihoods using both noise contrastive estimation (NCE) and score matching.<n>Our approach also exhibits effective transfer learning, generalizing to new systems at inference time and achieving at least a $6times$ speedup over standard MD.
  arXiv  Detail & Related papers  (2025-07-01T15:18:28Z)
• Score-Based Training for Energy-Based TTS Models [1.643629306994231]
  Noise contrastive estimation (NCE) is a popular method for training energy-based models (EBM) with intractable normalisation terms.<n>This paper proposes a new criterion that learns scores more suitable for first-order schemes.
  arXiv  Detail & Related papers  (2025-05-19T23:12:25Z)
• Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts [64.34482582690927]
  We provide an efficient and principled method for sampling from a sequence of annealed, geometric-averaged, or product distributions derived from pretrained score-based models.<n>We propose Sequential Monte Carlo (SMC) resampling algorithms that leverage inference-time scaling to improve sampling quality.
  arXiv  Detail & Related papers  (2025-03-04T17:46:51Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood [64.95663299945171]
  Training energy-based models (EBMs) on high-dimensional data can be both challenging and time-consuming. There exists a noticeable gap in sample quality between EBMs and other generative frameworks like GANs and diffusion models. We propose cooperative diffusion recovery likelihood (CDRL), an effective approach to tractably learn and sample from a series of EBMs.
  arXiv  Detail & Related papers  (2023-09-10T22:05:24Z)
• MCMC-Correction of Score-Based Diffusion Models for Model Composition [2.682859657520006]
  Diffusion models can be parameterized in terms of a score or an energy function.<n>We introduce a novel MH-like acceptance rule based on line integration of the score function.
  arXiv  Detail & Related papers  (2023-07-26T07:50:41Z)
• Efficient Training of Energy-Based Models Using Jarzynski Equality [13.636994997309307]
  Energy-based models (EBMs) are generative models inspired by statistical physics. The computation of its gradient with respect to the model parameters requires sampling the model distribution. Here we show how results for nonequilibrium thermodynamics based on Jarzynski equality can be used to perform this computation efficiently.
  arXiv  Detail & Related papers  (2023-05-30T21:07:52Z)
• Moment Matching Denoising Gibbs Sampling [14.75945343063504]
  Energy-Based Models (EBMs) offer a versatile framework for modeling complex data distributions. The widely-used Denoising Score Matching (DSM) method for scalable EBM training suffers from inconsistency issues. We propose an efficient sampling framework: (pseudo)-Gibbs sampling with moment matching.
  arXiv  Detail & Related papers  (2023-05-19T12:58:25Z)
• Self-Adapting Noise-Contrastive Estimation for Energy-Based Models [0.0]
  Training energy-based models with noise-contrastive estimation (NCE) is theoretically feasible but practically challenging. Previous works have explored modelling the noise distribution as a separate generative model, and then concurrently training this noise model with the EBM. This thesis proposes a self-adapting NCE algorithm which uses static instances of the EBM along its training trajectory as the noise distribution.
  arXiv  Detail & Related papers  (2022-11-03T15:17:43Z)
• 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)

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.