paper-with-me

홈 › Papers

Quantifying Epistemic Uncertainty in Diffusion Models

2026-02-09 · Aditi Gupta, Raphael A. Meyer, Yotam Yaniv, Elynn Chen, N. Benjamin Erichson arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.09170

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation

2023-08-15 · Jadie Adams, Shireen Y. Elhabian

Deep learning based methods for automatic organ segmentation have shown promise in aiding diagnosis and treatment planning. However, quantifying and understanding the uncertainty associated with model predictions is cruc…

BenchmarkingMedical Image AnalysisOrgan SegmentationOut-of-Distribution Detection+2

Do you understand epistemic uncertainty? Think again! Rigorous frequentist epistemic uncertainty estimation in regression

2025-03-17 · Enrico Foglia, Benjamin Bobbia, Nikita Durasov, Michael Bauerheim 외

Quantifying model uncertainty is critical for understanding prediction reliability, yet distinguishing between aleatoric and epistemic uncertainty remains challenging. We extend recent work from classification to regress…

regression

SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates

2020-08-24 · ICML 2020 1 · Lingkai Kong, Jimeng Sun, Chao Zhang

Uncertainty quantification is a fundamental yet unsolved problem for deep learning. The Bayesian framework provides a principled way of uncertainty estimation but is often not scalable to modern deep neural nets (DNNs) t…

Uncertainty Quantification

Energy-based Epistemic Uncertainty for Graph Neural Networks

2024-06-06 · Dominik Fuchsgruber, Tom Wollschläger, Stephan Günnemann

In domains with interdependent data, such as graphs, quantifying the epistemic uncertainty of a Graph Neural Network (GNN) is challenging as uncertainty can arise at different structural scales. Existing techniques negle…

Graph Neural Network

A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications

2021-11-03 · Xinlei Zhou, Han Liu, Farhad Pourpanah, Tieyong Zeng 외

Quantifying the uncertainty of supervised learning models plays an important role in making more reliable predictions. Epistemic uncertainty, which usually is due to insufficient knowledge about the model, can be reduced…