Unified Probabilistic Neural Architecture and Weight Ensembling Improves Model Robustness
This work addresses robustness for safety-critical applications by combining architecture and weight ensembling, offering an incremental advance over existing probabilistic methods.
The paper tackled the problem of improving model robustness by addressing epistemic uncertainty from both architecture and weight spaces, resulting in significant improvements in accuracy and calibration on CIFAR-10 and CIFAR-10-C datasets.
Robust machine learning models with accurately calibrated uncertainties are crucial for safety-critical applications. Probabilistic machine learning and especially the Bayesian formalism provide a systematic framework to incorporate robustness through the distributional estimates and reason about uncertainty. Recent works have shown that approximate inference approaches that take the weight space uncertainty of neural networks to generate ensemble prediction are the state-of-the-art. However, architecture choices have mostly been ad hoc, which essentially ignores the epistemic uncertainty from the architecture space. To this end, we propose a Unified probabilistic architecture and weight ensembling Neural Architecture Search (UraeNAS) that leverages advances in probabilistic neural architecture search and approximate Bayesian inference to generate ensembles form the joint distribution of neural network architectures and weights. The proposed approach showed a significant improvement both with in-distribution (0.86% in accuracy, 42% in ECE) CIFAR-10 and out-of-distribution (2.43% in accuracy, 30% in ECE) CIFAR-10-C compared to the baseline deterministic approach.