Uncertainty Quantification in CNN Through the Bootstrap of Convex Neural Networks
It addresses the lack of theoretically consistent uncertainty quantification for CNNs, which is critical for high-stakes applications like medicine.
The paper proposes a bootstrap-based framework for uncertainty quantification in CNNs, using convexified neural networks to achieve theoretical consistency. The method reduces computational load via warm-starts and transfer learning, outperforming baselines on image datasets.
Despite the popularity of Convolutional Neural Networks (CNN), the problem of uncertainty quantification (UQ) of CNN has been largely overlooked. Lack of efficient UQ tools severely limits the application of CNN in certain areas, such as medicine, where prediction uncertainty is critically important. Among the few existing UQ approaches that have been proposed for deep learning, none of them has theoretical consistency that can guarantee the uncertainty quality. To address this issue, we propose a novel bootstrap based framework for the estimation of prediction uncertainty. The inference procedure we use relies on convexified neural networks to establish the theoretical consistency of bootstrap. Our approach has a significantly less computational load than its competitors, as it relies on warm-starts at each bootstrap that avoids refitting the model from scratch. We further explore a novel transfer learning method so our framework can work on arbitrary neural networks. We experimentally demonstrate our approach has a much better performance compared to other baseline CNNs and state-of-the-art methods on various image datasets.