Efficient Controllable Diffusion via Optimal Classifier Guidance

• URL: http://arxiv.org/abs/2505.21666v1
• Date: Tue, 27 May 2025 18:46:21 GMT
• Title: Efficient Controllable Diffusion via Optimal Classifier Guidance
• Authors: Owen Oertell, Shikun Sun, Yiding Chen, Jin Peng Zhou, Zhiyong Wang, Wen Sun,
• Abstract summary: controllable generation of diffusion models aims to steer the model to generate samples that optimize some given objective functions.<n>We present SLCD -- Supervised Learning based Controllable Diffusion.
• Score: 16.748525985158278
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The controllable generation of diffusion models aims to steer the model to generate samples that optimize some given objective functions. It is desirable for a variety of applications including image generation, molecule generation, and DNA/sequence generation. Reinforcement Learning (RL) based fine-tuning of the base model is a popular approach but it can overfit the reward function while requiring significant resources. We frame controllable generation as a problem of finding a distribution that optimizes a KL-regularized objective function. We present SLCD -- Supervised Learning based Controllable Diffusion, which iteratively generates online data and trains a small classifier to guide the generation of the diffusion model. Similar to the standard classifier-guided diffusion, SLCD's key computation primitive is classification and does not involve any complex concepts from RL or control. Via a reduction to no-regret online learning analysis, we show that under KL divergence, the output from SLCD provably converges to the optimal solution of the KL-regularized objective. Further, we empirically demonstrate that SLCD can generate high quality samples with nearly the same inference time as the base model in both image generation with continuous diffusion and biological sequence generation with discrete diffusion. Our code is available at https://github.com/Owen-Oertell/slcd

Related papers

• Generative diffusion model with inverse renormalization group flows [0.0]
  Diffusion models produce data by denoising a sample corrupted by white noise.<n>We introduce a renormalization group-based diffusion model that leverages multiscale nature of data distributions.<n>We validate the versatility of the model through applications to protein structure prediction and image generation.
  arXiv  Detail & Related papers  (2025-01-15T19:00:01Z)
• Self-Guidance: Boosting Flow and Diffusion Generation on Their Own [32.91402070439289]
  Self-Guidance (SG) improves the image quality by suppressing the generation of low-quality samples.<n>We conduct experiments on text-to-image and text-to-video generation with different architectures.
  arXiv  Detail & Related papers  (2024-12-08T06:32:27Z)
• Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization [97.35427957922714]
  We present an algorithm named pairwise sample optimization (PSO), which enables the direct fine-tuning of an arbitrary timestep-distilled diffusion model.<n>PSO introduces additional reference images sampled from the current time-step distilled model, and increases the relative likelihood margin between the training images and reference images.<n>We show that PSO can directly adapt distilled models to human-preferred generation with both offline and online-generated pairwise preference image data.
  arXiv  Detail & Related papers  (2024-10-04T07:05:16Z)
• 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)
• Adding Conditional Control to Diffusion Models with Reinforcement Learning [68.06591097066811]
  Diffusion models are powerful generative models that allow for precise control over the characteristics of the generated samples.<n>While these diffusion models trained on large datasets have achieved success, there is often a need to introduce additional controls in downstream fine-tuning processes.<n>This work presents a novel method based on reinforcement learning (RL) to add such controls using an offline dataset.
  arXiv  Detail & Related papers  (2024-06-17T22:00:26Z)
• Guided Diffusion from Self-Supervised Diffusion Features [49.78673164423208]
  Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or pretraining. We propose a framework to extract guidance from, and specifically for, diffusion models.
  arXiv  Detail & Related papers  (2023-12-14T11:19:11Z)
• Your Diffusion Model is Secretly a Zero-Shot Classifier [90.40799216880342]
  We show that density estimates from large-scale text-to-image diffusion models can be leveraged to perform zero-shot classification. Our generative approach to classification attains strong results on a variety of benchmarks. Our results are a step toward using generative over discriminative models for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T17:59:56Z)

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.