论文标题
通过校准预测，PAC置信度设置为深神经网络
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
论文作者
论文摘要
我们提出了一种结合了学习理论的校准预测和概括界限到具有PAC保证的深神经网络的置信集的算法 - 即，给定输入的置信设置包含具有很高可能性的真实标签。我们演示了如何使用我们的方法来构建Imagenet Resnet上的PAC置信度集，视觉对象跟踪模型以及半cheetah增强学习问题的动态模型。
We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i.e., the confidence set for a given input contains the true label with high probability. We demonstrate how our approach can be used to construct PAC confidence sets on ResNet for ImageNet, a visual object tracking model, and a dynamics model for the half-cheetah reinforcement learning problem.
