egobox-ego
| Crates.io | egobox-ego |
| lib.rs | egobox-ego |
| version | 0.24.0 |
| source | src |
| created_at | 2022-04-12 13:53:12.93305 |
| updated_at | 2024-11-12 16:06:52.870032 |
| description | A library for efficient global optimization |
| homepage | |
| repository | https://github.com/relf/egobox |
| max_upload_size | |
| id | 566443 |
| size | 305,596 |
Rémi Lafage (relf)
documentation
README
Efficient global optimization
egobox-ego provides a Rust implementation of efficient global optimization algorithm.
It is a Rust port of EGO of the SMT Python library.
The big picture
egobox-ego is a library crate in the top-level package egobox.
Current state
egobox-ego currently implements EGO using egobox-moe with the following features:
- Mixture of gausian processes
- Infill criteria: EI, WB2, WB2S
- Basic handling of negative constraints
- Mixed integer optimization available through continuous relaxation
- Trust region EGO algorithm
Examples
There is some usage examples in the examples/ directory. To run, use:
cargo run --release --example ackley
License
Licensed under the Apache License, Version 2.0 http://www.apache.org/licenses/LICENSE-2.0