Timezone: »

 
Towards Robust and Automatic Hyper-Parameter Tunning
Mathieu Tuli · Mahdi Hosseini · Konstantinos N Plataniotis

The task of hyper-parameter optimization (HPO) is burdened with heavy computational costs due to the intractability of optimizing both a model's weights and its hyper-parameters simultaneously. In this work, we introduce a new class of HPO method and explore how the low-rank factorization of the convolutional weights of intermediate layers of a convolutional neural network can be used to define an analytical response surface for optimizing hyper-parameters, using only training data. We quantify how this surface behaves as a surrogate to model performance and can be solved using a trust-region search algorithm, which we call \AlgName. The algorithm outperforms state-of-the-art such as Bayesian Optimization and generalizes across model, optimizer, and dataset selection.

Author Information

Mathieu Tuli (University of Toronto and Vector Institute)
Mahdi Hosseini (University of New Brunswick)
Konstantinos N Plataniotis (UofT)

More from the Same Authors