Tutorials

BOSS supports running either via a simple command-line interface (CLI) or directly in Python scripts using the Python application programming interface (API). Several tutorials are available below for both modes of running, with emphasis on the practicalities of using the code. In both modes, BOSS settings such as the number of iterations, key algorithms, variable input and so on, can be conveniently controlled through BOSS keywords, some of which are necessary to start the active learning simulation.

Command-line interface and Python API

The BOSS CLI is provided by an executable called boss that is automatically generated during the installation process. The function to be optimized must be defined in Python, but once this is done, the user is free to run BOSS from the command line without interacting with Python at all. Conversely, with Python API all BOSS functionalities can be executed within Python.

To get started with the BOSS binary, see the following pages for CLI and API:

• Quickstart ( CLI | API )

• Post-processing ( CLI | API )

• Restarting ( CLI | API )

• Results ( API )

A set of more in-depth tutorials are also available for download:

• Tutorial 1: Introduction to BOSS input files, user function, and postprocessing ( CLI | API )

• Tutorial 2: Alanine conformer search in 2D and 4D, using the AMBER code ( CLI | API )

• Tutorial 3: Using existing data to find minima and illustrate landscapes ( CLI | API )

Advanced features

BOSS also supports a number of more advanced features. The following tutorials are for the API, but the keywords are generally the same for CLI:

• Batch acquisitions
• Cost functions
• User function symmetry
• Gradient observations
• Multi-fidelity optimization
• Heteroscedastic noise
  • Example 1: Simple noise function
  • Example 2: Known noise of initial data
• Pareto front analysis

Further reading

If you wish to learn more about Gaussian processes and Bayesian optimization, we recommend the following resources:

• Visual/Interactive introduction to Gaussian Processes

• Visual/Interactive introduction to Bayesian optimization

• C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning, MIT Press (2006).

• E. Brochu et al., A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning (2010).

• R. Garnett, Bayesian Optimization, Cambridge University Press (2022).

• P. I. Frazier and J. Wang, Bayesian optimization for materials design (2015).