提出自适应先验框架，提升分布偏移下的不确定性估计可靠性。
Quantifying Uncertainty in the Presence of Distribution Shifts
- 用训练与新数据共同决定的自适应先验，动态调整不确定性
- 在分布偏移下，不确定性估计显著优于传统方法
- 适合关注模型可信度的工业部署与安全敏感场景
神经网络虽能做出准确预测，但在训练与测试数据分布发生偏移时，往往无法提供可靠的不确定性估计。为此，我们提出一种贝叶斯框架，显式建模协变量分布偏移。不同于传统固定先验，本方法采用基于训练数据和新输入的自适应先验，使远离训练分布的输入自动产生更高不确定性，反映预测性能可能下降的区域。为高效逼近后验预测分布，我们采用摊销变分推断。最后，通过从训练数据中抽取小规模自助样本，构建合成环境，仅用原始数据模拟多种可能的分布偏移。在合成与真实数据上评估均表明，该方法在分布偏移下显著提升了不确定性估计质量。
原文摘要 · Abstract (English)
Neural networks make accurate predictions but often fail to provide reliable uncertainty estimates, especially under covariate distribution shifts between training and testing. To address this problem, we propose a Bayesian framework for uncertainty estimation that explicitly accounts for covariate shifts. While conventional approaches rely on fixed priors, the key idea of our method is an adaptive prior, conditioned on both training and new covariates. This prior naturally increases uncertainty for inputs that lie far from the training distribution in regions where predictive performance is likely to degrade. To efficiently approximate the resulting posterior predictive distribution, we employ amortized variational inference. Finally, we construct synthetic environments by drawing small bootstrap samples from the training data, simulating a range of plausible covariate shift using only the original dataset. We evaluate our method on both synthetic and real-world data. It yields substantially improved uncertainty estimates under distribution shifts.
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。