Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review

• URL: http://arxiv.org/abs/2501.09685v2
• Date: Mon, 20 Jan 2025 22:00:26 GMT
• Title: Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
• Authors: Masatoshi Uehara, Yulai Zhao, Chenyu Wang, Xiner Li, Aviv Regev, Sergey Levine, Tommaso Biancalani,
• Abstract summary: This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. practical applications in fields such as biology often require sample generation that maximizes specific metrics. We discuss (1) fine-tuning methods combined with inference-time techniques, (2) inference-time algorithms based on search algorithms such as Monte Carlo tree search, and (3) connections between inference-time algorithms in language models and diffusion models.
• Score: 59.856222854472605
• License:
• Abstract: This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are renowned for their generative modeling capabilities, practical applications in fields such as biology often require sample generation that maximizes specific metrics (e.g., stability, affinity in proteins, closeness to target structures). In these scenarios, diffusion models can be adapted not only to generate realistic samples but also to explicitly maximize desired measures at inference time without fine-tuning. This tutorial explores the foundational aspects of such inference-time algorithms. We review these methods from a unified perspective, demonstrating that current techniques -- such as Sequential Monte Carlo (SMC)-based guidance, value-based sampling, and classifier guidance -- aim to approximate soft optimal denoising processes (a.k.a. policies in RL) that combine pre-trained denoising processes with value functions serving as look-ahead functions that predict from intermediate states to terminal rewards. Within this framework, we present several novel algorithms not yet covered in the literature. Furthermore, we discuss (1) fine-tuning methods combined with inference-time techniques, (2) inference-time algorithms based on search algorithms such as Monte Carlo tree search, which have received limited attention in current research, and (3) connections between inference-time algorithms in language models and diffusion models. The code of this tutorial on protein design is available at https://github.com/masa-ue/AlignInversePro

Related papers

• Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms [31.42317398879432]
  Current inference approaches mainly fall into two categories: exact simulation and approximate methods such as $tau$-leaping. In this work, we advance the latter category by tailoring the first extension of high-order numerical inference schemes to discrete diffusion models. We rigorously analyze the proposed schemes and establish the second-order accuracy of the $theta$-trapezoidal method in KL divergence.
  arXiv  Detail & Related papers  (2025-02-01T00:25:21Z)
• Fast constrained sampling in pre-trained diffusion models [77.21486516041391]
  Diffusion models have dominated the field of large, generative image models. We propose an algorithm for fast-constrained sampling in large pre-trained diffusion models.
  arXiv  Detail & Related papers  (2024-10-24T14:52:38Z)
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding [84.3224556294803]
  Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. We aim to optimize downstream reward functions while preserving the naturalness of these design spaces. Our algorithm integrates soft value functions, which looks ahead to how intermediate noisy states lead to high rewards in the future.
  arXiv  Detail & Related papers  (2024-08-15T16:47:59Z)
• Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review [63.31328039424469]
  This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. We explain the application of various RL algorithms, including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
  arXiv  Detail & Related papers  (2024-07-18T17:35:32Z)
• Faster Adaptive Federated Learning [84.38913517122619]
  Federated learning has attracted increasing attention with the emergence of distributed data. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on momentum-based variance reduced technique in cross-silo FL.
  arXiv  Detail & Related papers  (2022-12-02T05:07:50Z)
• Fast Sampling of Diffusion Models via Operator Learning [74.37531458470086]
  We use neural operators, an efficient method to solve the probability flow differential equations, to accelerate the sampling process of diffusion models. Compared to other fast sampling methods that have a sequential nature, we are the first to propose a parallel decoding method. We show our method achieves state-of-the-art FID of 3.78 for CIFAR-10 and 7.83 for ImageNet-64 in the one-model-evaluation setting.
  arXiv  Detail & Related papers  (2022-11-24T07:30:27Z)
• Sparse Algorithms for Markovian Gaussian Processes [18.999495374836584]
  Sparse Markovian processes combine the use of inducing variables with efficient Kalman filter-likes recursion. We derive a general site-based approach to approximate the non-Gaussian likelihood with local Gaussian terms, called sites. Our approach results in a suite of novel sparse extensions to algorithms from both the machine learning and signal processing, including variational inference, expectation propagation, and the classical nonlinear Kalman smoothers. The derived methods are suited to literature-temporal data, where the model has separate inducing points in both time and space.
  arXiv  Detail & Related papers  (2021-03-19T09:50:53Z)
• Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie [13.476505672245603]
  This paper develops theory, methods, and provably convergent algorithms for performing Bayesian inference with priors. We introduce two algorithms: 1) -ULA (Unadjusted Langevin) Algorithm inference for Monte Carlo sampling and MMSE; and 2) quantitative-SGD (Stochastic Gradient Descent) for inference. The algorithms are demonstrated on several problems such as image denoisering, inpainting, and denoising, where they are used for point estimation as well as for uncertainty visualisation and regularity.
  arXiv  Detail & Related papers  (2021-03-08T12:46:53Z)

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.