PyTorch Hyperparameter Tuning - A Tutorial for spotPython

by   Thomas Bartz-Beielstein, et al.

The goal of hyperparameter tuning (or hyperparameter optimization) is to optimize the hyperparameters to improve the performance of the machine or deep learning model. spotPython (“Sequential Parameter Optimization Toolbox in Python”) is the Python version of the well-known hyperparameter tuner SPOT, which has been developed in the R programming environment for statistical analysis for over a decade. PyTorch is an optimized tensor library for deep learning using GPUs and CPUs. This document shows how to integrate the spotPython hyperparameter tuner into the PyTorch training workflow. As an example, the results of the CIFAR10 image classifier are used. In addition to an introduction to spotPython, this tutorial also includes a brief comparison with Ray Tune, a Python library for running experiments and tuning hyperparameters. This comparison is based on the PyTorch hyperparameter tuning tutorial. The advantages and disadvantages of both approaches are discussed. We show that spotPython achieves similar or even better results while being more flexible and transparent than Ray Tune.


page 25

page 26

page 27

page 28


Guided Hyperparameter Tuning Through Visualization and Inference

For deep learning practitioners, hyperparameter tuning for optimizing mo...

Improving Deep Learning for Defect Prediction (using the GHOST Hyperparameter Optimizer)

There has been much recent interest in the application of deep learning ...

Hyperparameter Tuning Cookbook: A guide for scikit-learn, PyTorch, river, and spotPython

This document provides a comprehensive guide to hyperparameter tuning us...

Discrete Simulation Optimization for Tuning Machine Learning Method Hyperparameters

Machine learning methods are being increasingly used in most technical a...

Fast Hyperparameter Tuning for Ising Machines

In this paper, we propose a novel technique to accelerate Ising machines...

Tune: A Research Platform for Distributed Model Selection and Training

Modern machine learning algorithms are increasingly computationally dema...

Tune As You Scale: Hyperparameter Optimization For Compute Efficient Training

Hyperparameter tuning of deep learning models can lead to order-of-magni...

Please sign up or login with your details

Forgot password? Click here to reset