Skip to content

Commit 8cb52b4

Browse files
v0.2.20
docs updated
1 parent 5071c69 commit 8cb52b4

42 files changed

Lines changed: 3112 additions & 6080 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

README.md

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,9 @@ Sequential Parameter Optimization in Python
1818

1919
# spotPython Documentation
2020

21-
* [Bartz-Beielstein (2023). PyTorch Hyperparameter Tuning --- A Tutorial for spotPython (Working Paper)](https://sequential-parameter-optimization.github.io/spotPython/).
21+
* Hyperparameter-tuning Cookbook: A guide for scikit-learn, PyTorch, river, and spotPython. Available at [https://sequential-parameter-optimization.github.io/spotPython/](https://sequential-parameter-optimization.github.io/spotPython/).
22+
23+
* [Bartz-Beielstein (2023). PyTorch Hyperparameter Tuning --- A Tutorial for spotPython (Working Paper)](https://arxiv.org/abs/2305.11930).
2224

2325
> **Abstract**: 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.
2426

@@ -33,6 +35,7 @@ Sequential Parameter Optimization in Python
3335
- Simple JSON files for the specification of the hyperparameters.
3436
- Extension of default and user specified network classes.
3537
- Noise handling techniques.
38+
- Tensorboard interaction.
3639

3740
# Citation
3841

docs/01_spot_intro.html

Lines changed: 138 additions & 75 deletions
Large diffs are not rendered by default.

docs/02_spot_multidim.html

Lines changed: 56 additions & 85 deletions
Large diffs are not rendered by default.

docs/03_spot_anisotropic.html

Lines changed: 53 additions & 111 deletions
Large diffs are not rendered by default.

docs/04_spot_sklearn_surrogate.html

Lines changed: 84 additions & 157 deletions
Large diffs are not rendered by default.
-17 Bytes
Loading
-3 Bytes
Loading
3 Bytes
Loading
852 Bytes
Loading
-32 Bytes
Loading

0 commit comments

Comments
 (0)