On scalable and efficient training of diffusion samplers

• URL: http://arxiv.org/abs/2505.19552v2
• Date: Sat, 31 May 2025 14:12:47 GMT
• Title: On scalable and efficient training of diffusion samplers
• Authors: Minkyu Kim, Kiyoung Seong, Dongyeop Woo, Sungsoo Ahn, Minsu Kim,
• Abstract summary: We address the challenge of training diffusion models to sample from unnormalized energy distributions in the absence of data.<n>We propose a scalable and sample-efficient framework that properly harmonizes the powerful classical sampling method and the diffusion sampler.<n>Our method significantly improves sample efficiency on standard benchmarks for diffusion samplers and also excels at higher-dimensional problems and real-world molecular conformer generation.
• Score: 26.45926098524023
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We address the challenge of training diffusion models to sample from unnormalized energy distributions in the absence of data, the so-called diffusion samplers. Although these approaches have shown promise, they struggle to scale in more demanding scenarios where energy evaluations are expensive and the sampling space is high-dimensional. To address this limitation, we propose a scalable and sample-efficient framework that properly harmonizes the powerful classical sampling method and the diffusion sampler. Specifically, we utilize Monte Carlo Markov chain (MCMC) samplers with a novelty-based auxiliary energy as a Searcher to collect off-policy samples, using an auxiliary energy function to compensate for exploring modes the diffusion sampler rarely visits. These off-policy samples are then combined with on-policy data to train the diffusion sampler, thereby expanding its coverage of the energy landscape. Furthermore, we identify primacy bias, i.e., the preference of samplers for early experience during training, as the main cause of mode collapse during training, and introduce a periodic re-initialization trick to resolve this issue. Our method significantly improves sample efficiency on standard benchmarks for diffusion samplers and also excels at higher-dimensional problems and real-world molecular conformer generation.

Related papers

• Adjoint Schrödinger Bridge Sampler [27.07623265593163]
  Adjoint Schr"odinger Bridge Sampler (ASBS) is a new diffusion sampler that employs simple and scalable matching-based objectives.<n>ASBS is grounded on a mathematical model -- the Schr"odinger Bridge -- which enhances sampling efficiency via kinetic-optimal transportation.
  arXiv  Detail & Related papers  (2025-06-27T18:27:59Z)
• Non-equilibrium Annealed Adjoint Sampler [27.73022309947818]
  We introduce the textbfNon-equilibrium Annealed Adjoint Sampler (NAAS), a novel SOC-based diffusion sampler.<n> NAAS employs a lean adjoint system inspired by adjoint matching, enabling efficient and scalable training.
  arXiv  Detail & Related papers  (2025-06-22T20:41:31Z)
• Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities [85.83359661628575]
  We propose Progressive Inference-Time Annealing (PITA) to learn diffusion-based samplers.<n>PITA combines two complementary techniques: Annealing of the Boltzmann distribution and Diffusion smoothing.<n>It enables equilibrium sampling of N-body particle systems, Alanine Dipeptide, and tripeptides in Cartesian coordinates.
  arXiv  Detail & Related papers  (2025-06-19T17:14:22Z)
• Adaptive Destruction Processes for Diffusion Samplers [12.446080077998834]
  This paper explores the challenges and benefits of a trainable destruction process in diffusion samplers.<n>We show that, when the number of steps is limited, training both generation and destruction processes results in faster convergence and improved sampling quality.
  arXiv  Detail & Related papers  (2025-06-02T11:07:27Z)
• Single-Step Consistent Diffusion Samplers [8.758218443992467]
  Existing sampling algorithms typically require many iterative steps to produce high-quality samples.<n>We introduce consistent diffusion samplers, a new class of samplers designed to generate high-fidelity samples in a single step.<n>We show that our approach yields high-fidelity samples using less than 1% of the network evaluations required by traditional diffusion samplers.
  arXiv  Detail & Related papers  (2025-02-11T14:25:52Z)
• Adaptive teachers for amortized samplers [76.88721198565861]
  We propose an adaptive training distribution (the teacher) to guide the training of the primary amortized sampler (the student)<n>We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge.
  arXiv  Detail & Related papers  (2024-10-02T11:33:13Z)
• 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)
• 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.<n>We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods.<n>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)
• Simple and effective data augmentation for compositional generalization [64.00420578048855]
  We show that data augmentation methods that sample MRs and backtranslate them can be effective for compositional generalization. Remarkably, sampling from a uniform distribution performs almost as well as sampling from the test distribution.
  arXiv  Detail & Related papers  (2024-01-18T09:13:59Z)
• Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation [53.27596811146316]
  Diffusion models operate over a sequence of timesteps instead of instantaneous input-output relationships in previous contexts. We present Diffusion-TracIn that incorporates this temporal dynamics and observe that samples' loss gradient norms are highly dependent on timestep. We introduce Diffusion-ReTrac as a re-normalized adaptation that enables the retrieval of training samples more targeted to the test sample of interest.
  arXiv  Detail & Related papers  (2024-01-17T07:58:18Z)
• Entropy-based Training Methods for Scalable Neural Implicit Sampler [15.978655106034113]
  Efficiently sampling from un-normalized target distributions is a fundamental problem in scientific computing and machine learning. In this paper, we propose an efficient and scalable neural implicit sampler that overcomes these limitations. Our sampler can generate large batches of samples with low computational costs by leveraging a neural transformation that directly maps easily sampled latent vectors to target samples.
  arXiv  Detail & Related papers  (2023-06-08T05:56:05Z)

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.