Timezone: »

Unified Probabilistic Neural Architecture and Weight Ensembling Improves Model Robustness
Sumegha Premchandar · Sanket Jantre · Prasanna Balaprakash · Sandeep Madireddy
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.


#### Author Information

##### Prasanna Balaprakash (Argonne National Laboratory)

Prasanna Balaprakash is a computer scientist with a joint appointment in the Mathematics and Computer Science Division and the Leadership Computing Facility at Argonne National Laboratory. His research interests span the areas of artificial intelligence, machine learning, optimization, and supercomputing. His research focuses on the development of AI methods for scientific applications. He is a recipient of U.S. Department of Energy 2018 Early Career Award. Prior to Argonne, he worked as a Chief Technology Officer at Mentis Sprl, a machine learning startup in Brussels, Belgium. He received his PhD from CoDE-IRIDIA (AI Lab), Université Libre de Bruxelles, Brussels, Belgium, where he was a recipient of Marie Curie and F.R.S-FNRS Aspirant fellowships.