Model Uncertainty-Aware Differentiable Architecture Search
Author(s)
Chakraborty, Biswadeep
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
We present a Model Uncertainty-aware Differentiable ARchiTecture Search (μDARTS) that optimizes neural networks to achieve high accuracy and low uncertainty simultaneously. We introduce concrete dropout within DARTS cells and include a Monte-Carlo regularizer within the training loss to optimize the concrete dropout probabilities. A predictive variance term is introduced in the validation loss to enable searching for architecture with minimal model uncertainty. The experiments on CIFAR10, CIFAR100, SVHN, and ImageNet verify the effectiveness of μDARTS in improving accuracy and reducing uncertainty compared to existing DARTS methods. Moreover, the final architecture obtained from μDARTS shows higher robustness to noise at the input image and model parameters compared to the architecture obtained from existing DARTS methods.
Sponsor
Date
2023-12-05
Extent
Resource Type
Text
Resource Subtype
Thesis