提出新方法分离扩散模型的确定性不确定性，提升生成结果可信度。
Quantifying Epistemic Uncertainty in Diffusion Models
- 基于Fisher信息设计方法，明确分离确定性不确定性
- 在合成时间序列任务中，显著提升不确定性估计准确性
- 适合关注生成质量可靠性与可信评估的研究者
为确保生成结果高质量，量化扩散模型的确定性不确定性至关重要。现有方法常将确定性与偶然性不确定性混杂，导致不可靠。本文提出基于Fisher信息的方法，显式分离确定性方差，生成更可靠的生成数据可信度评分。为实现可扩展性，引入FLARE（Fisher-Laplace随机估计器），通过均匀随机子集近似Fisher信息。实验表明，FLARE在合成时间序列生成任务中优于其他方法，实现更准确、可靠的过滤。理论分析给出了随机近似的收敛速率界，并提供解析与实证证据，证明仅用最后一层拉普拉斯近似不足以完成此任务。
原文摘要 · Abstract (English)
To ensure high quality outputs, it is important to quantify the epistemic uncertainty of diffusion models. Existing methods are often unreliable because they mix epistemic and aleatoric uncertainty. We introduce a method based on Fisher information that explicitly isolates epistemic variance, producing more reliable plausibility scores for generated data. To make this approach scalable, we propose FLARE (Fisher-Laplace Randomized Estimator), which approximates the Fisher information using a uniformly random subset of model parameters. Empirically, FLARE improves uncertainty estimation in synthetic time-series generation tasks, achieving more accurate and reliable filtering than other methods. Theoretically, we bound the convergence rate of our randomized approximation and provide analytic and empirical evidence that last-layer Laplace approximations are insufficient for this task.
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。