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}.
@article{arxiv.2111.14056,
title = {Towards Robust and Automatic Hyper-Parameter Tunning},
author = {Mathieu Tuli and Mahdi S. Hosseini and Konstantinos N. Plataniotis},
journal= {arXiv preprint arXiv:2111.14056},
year = {2021}
}
Comments
NeurIPS-OPT2021: 13th Annual Workshop on Optimization for Machine Learning