Hyperparameter Ensembles for Robustness and Uncertainty Quantification
This work addresses the need for robust and uncertainty-aware models in machine learning, offering incremental improvements over existing ensemble methods.
The paper tackles the problem of improving neural network ensembles by incorporating hyperparameter diversity, proposing hyper-deep ensembles and hyper-batch ensembles, which achieve state-of-the-art accuracy and calibration on image classification tasks with various architectures.
Ensembles over neural network weights trained from different random initialization, known as deep ensembles, achieve state-of-the-art accuracy and calibration. The recently introduced batch ensembles provide a drop-in replacement that is more parameter efficient. In this paper, we design ensembles not only over weights, but over hyperparameters to improve the state of the art in both settings. For best performance independent of budget, we propose hyper-deep ensembles, a simple procedure that involves a random search over different hyperparameters, themselves stratified across multiple random initializations. Its strong performance highlights the benefit of combining models with both weight and hyperparameter diversity. We further propose a parameter efficient version, hyper-batch ensembles, which builds on the layer structure of batch ensembles and self-tuning networks. The computational and memory costs of our method are notably lower than typical ensembles. On image classification tasks, with MLP, LeNet, ResNet 20 and Wide ResNet 28-10 architectures, we improve upon both deep and batch ensembles.