Autotune: A Derivative-free Optimization Framework for Hyperparameter Tuning

by   Patrick Koch, et al.

Machine learning applications often require hyperparameter tuning. The hyperparameters usually drive both the efficiency of the model training process and the resulting model quality. For hyperparameter tuning, machine learning algorithms are complex black-boxes. This creates a class of challenging optimization problems, whose objective functions tend to be nonsmooth, discontinuous, unpredictably varying in computational expense, and include continuous, categorical, and/or integer variables. Further, function evaluations can fail for a variety of reasons including numerical difficulties or hardware failures. Additionally, not all hyperparameter value combinations are compatible, which creates so called hidden constraints. Robust and efficient optimization algorithms are needed for hyperparameter tuning. In this paper we present an automated parallel derivative-free optimization framework called Autotune, which combines a number of specialized sampling and search methods that are very effective in tuning machine learning models despite these challenges. Autotune provides significantly improved models over using default hyperparameter settings with minimal user interaction on real-world applications. Given the inherent expense of training numerous candidate models, we demonstrate the effectiveness of Autotune's search methods and the efficient distributed and parallel paradigms for training and tuning models, and also discuss the resource trade-offs associated with the ability to both distribute the training process and parallelize the tuning process.


page 1

page 2

page 3

page 4


Importance of Tuning Hyperparameters of Machine Learning Algorithms

The performance of many machine learning algorithms depends on their hyp...

Efficient Hyperparameter Tuning with Dynamic Accuracy Derivative-Free Optimization

Many machine learning solutions are framed as optimization problems whic...

Automatic Gradient Boosting

Automatic machine learning performs predictive modeling with high perfor...

A Region-Shrinking-Based Acceleration for Classification-Based Derivative-Free Optimization

Derivative-free optimization algorithms play an important role in scient...

Massively Parallel Hyperparameter Tuning

Modern learning models are characterized by large hyperparameter spaces....

Automatically Bounding the Taylor Remainder Series: Tighter Bounds and New Applications

We present a new algorithm for automatically bounding the Taylor remaind...

Please sign up or login with your details

Forgot password? Click here to reset