Towards Robust and Automatic Hyper-Parameter Tunning
This addresses the problem of efficient hyper-parameter tuning for machine learning practitioners, offering a novel approach that reduces computational burden.
The paper tackles the computational cost of hyper-parameter optimization by introducing autoHyper, a method that uses low-rank factorization of convolutional weights to create an analytical response surface for optimizing hyper-parameters, outperforming Bayesian Optimization and generalizing across models, optimizers, and datasets.
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 autoHyper. The algorithm outperforms state-of-the-art such as Bayesian Optimization and generalizes across model, optimizer, and dataset selection. Our code can be found at \url{https://github.com/MathieuTuli/autoHyper}.