# JasperSnoek/spearmint

Spearmint is a package to perform Bayesian optimization according to the algorithms outlined in the paper:  Practical Bayesian Optimization of Machine Learning Algorithms. Jasper Snoek, Hugo Larochelle and Ryan P. Adams.  Advances in Neural Information Processing Systems, 2012

Repository: https://github.com/JasperSnoek/spearmint
Canonical: https://ross.abutalabs.com/products/jaspersnoek-spearmint
Homepage: http://people.seas.harvard.edu/~jsnoek/software.html
Language: Python
License Family: other
Last push: 2017-07-21T14:38:48+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4975, "days_push": 3330, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1392, forks 332 (observed 2026-08-28T04:04:36.110215+00:00)

## What it is
Spearmint is a Python package for Bayesian optimization of machine learning algorithms, iteratively tuning parameters to minimize an objective in as few experiment runs as possible. This is the original legacy repository, now maintained only for bug fixes, with development moved to the HIPS/Spearmint codebase.

## Use cases
- bayesian optimization of machine learning hyperparameters
- minimize an objective function in as few runs as possible
- automatically run and tune experiments in parallel
- tune parameters of expensive black-box functions
- hyperparameter search using expected improvement or UCB acquisition functions

## When to choose
- you need the original 2012 algorithms under a permissive license
- you want to swap out acquisition function and driver modules
- you must run optimization experiments in parallel on a machine or cluster

## When to avoid
- you need modern Python support (this requires Python 2.7)
- you want active development or new features
- you prefer the overhauled HIPS/Spearmint codebase
- you need commercial use of the newer implementation without license restrictions

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, benchmarking, cli
- domain: machine-learning, developer-tools
- platform: python
- tags: bayesian-optimization, hyperparameter-tuning, python2, legacy, algorithms, linux, macos

## Member repositories
- JasperSnoek/spearmint (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:36.110215+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:31.419971+00:00, confidence not recorded.
  - readme: https://github.com/JasperSnoek/spearmint (fetched 2026-08-28T04:04:36.110215+00:00, sha 2eadc9d86901)
- Data as of 2026-08-30T08:39:29.467469+00:00.