# Towards Robust and Automatic Hyper-Parameter Tunning

arXiv: https://arxiv.org/abs/2111.14056 · HTML: https://mlsanity.com/paper/2111.14056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 28 Nov 2021.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [The Marginal Value of Adaptive Gradient Methods in Machine Learning](https://mlsanity.com/paper/1705.08292/) (2017)
- [Adaptive Gradient Methods with Dynamic Bound of Learning Rate](https://mlsanity.com/paper/1902.09843/) (2019)
- [Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates](https://mlsanity.com/paper/1905.09997/) (2019)
- [On Empirical Comparisons of Optimizers for Deep Learning](https://mlsanity.com/paper/1910.05446/) (2019)
- [AdaS: Adaptive Scheduling of Stochastic Gradients](https://mlsanity.com/paper/2006.06587/) (2020)
- [CONet: Channel Optimization for Convolutional Neural Networks](https://mlsanity.com/paper/2108.06822/) (2021)
- [In Search of Probeable Generalization Measures](https://mlsanity.com/paper/2110.12259/) (2021)

## Abstract (arXiv)

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 urlhttps://github.com/MathieuTuli/autoHyper.