提出无需分布假设的不确定性量化方法，提升模型鲁棒性与可信度
Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data
- 采用pNML框架实现无分布假设下的个体化预测
- 在分布外检测、对抗攻击等任务中表现优于现有方法
- 适合需要高可信预测的医疗、金融等安全敏感场景
机器学习模型在多个领域表现出色，主流方法为经验风险最小化（ERM），其通过调整模型权重以降低训练集损失，并用于新数据的标签预测。然而，ERM假设测试分布与训练分布相似，这在真实场景中未必成立。相比之下，预测归一化最大似然（pNML）作为个体设置下的极小极大解，不依赖输入分布假设。本研究探讨了线性回归与神经网络在pNML下的可学习性，证明pNML能提升模型在多种任务中的性能与鲁棒性。此外，pNML能提供精确的置信度估计，在分布外检测、抵抗对抗攻击及主动学习方面均达到当前最优水平。
原文摘要 · Abstract (English)
Machine learning models have exhibited exceptional results in various domains. The most prevalent approach for learning is the empirical risk minimizer (ERM), which adapts the model's weights to reduce the loss on a training set and subsequently leverages these weights to predict the label for new test data. Nonetheless, ERM makes the assumption that the test distribution is similar to the training distribution, which may not always hold in real-world situations. In contrast, the predictive normalized maximum likelihood (pNML) was proposed as a min-max solution for the individual setting where no assumptions are made on the distribution of the tested input. This study investigates pNML's learnability for linear regression and neural networks, and demonstrates that pNML can improve the performance and robustness of these models on various tasks. Moreover, the pNML provides an accurate confidence measure for its output, showcasing state-of-the-art results for out-of-distribution detection, resistance to adversarial attacks, and active learning.
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。