提出校准的测试时引导方法，实现更准确的贝叶斯推断。
Calibrated Test-Time Guidance for Bayesian Inference
- 基于贝叶斯后验设计新估计器，修正现有方法的偏差
- 在贝叶斯任务中显著优于旧方法，黑洞图像重建PSNR达新高
- 适合需要可靠概率推理的科学建模与决策场景
测试时引导是广泛用于引导预训练扩散模型生成符合奖励函数结果的机制。然而，现有方法侧重于最大化奖励而非从真实贝叶斯后验采样，导致推断失准。本文揭示常见测试时引导方法无法恢复正确的后验分布，并指出其结构近似导致失败的原因。随后提出一致的替代估计器，实现从贝叶斯后验的校准采样。在一系列贝叶斯推断任务中显著优于先前方法，在黑洞图像重建任务中达到新的最优PSNR。
原文摘要 · Abstract (English)
Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on maximizing reward rather than sampling from the true Bayesian posterior, leading to miscalibrated inference. In this work, we show that common test-time guidance methods do not recover the correct posterior distribution and identify the structural approximations responsible for this failure. We then propose consistent alternative estimators that enable calibrated sampling from the Bayesian posterior. We significantly outperform previous methods on a set of Bayesian inference tasks, and set a new state-of-the-art PSNR in black hole image reconstruction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。