macOS
Homebrewverified · 100%
brew install liblinearprovider-native install command
brew / rank 448
Install liblinear with Homebrew
Library for large linear classification. Version 2.50 via Homebrew; verified from local package data.
install
Additional install commands
overview
Package summary
Library for large linear classification
Project links
Commands and aliases
- predict
- train
history
Project history and usage
LIBLINEAR is a National Taiwan University machine-learning package for large-scale regularized linear classification, regression, and outlier detection. It pairs a C/C++ library with simple command-line tools such as train and predict, making linear SVM and logistic-regression models accessible from scripts and other software.
Project history
The LIBLINEAR paper was submitted to the Journal of Machine Learning Research in May 2008 and published in August 2008 by Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. The paper presents LIBLINEAR as an open source library for large-scale linear classification with easy command-line tools and library calls.
LIBLINEAR was designed as a sibling to LIBSVM for cases where a linear model is appropriate and kernel methods are too expensive. The README explicitly advises beginners with small data sets to consider LIBSVM first, while pointing to LIBLINEAR for large data where nonlinear mappings do not materially improve performance.
The public GitHub mirror was created on May 19, 2014, giving the project a familiar source-control home for packagers and downstream wrappers.
Adoption history
LIBLINEAR spread through both command-line use and embedding. Its stable file format, simple executables, MATLAB/OCTAVE interface, Python interface, and C API made it easy to package and wrap.
One visible downstream adoption path is scikit-learn, whose LogisticRegression documentation exposes a 'liblinear' solver for L1 and L2 regularization. That made the project familiar even to Python users who never invoke the original train and predict binaries.
How it is used
The canonical workflow is to build the package with make, train a model from sparse feature data using train, and apply the model with predict. The README describes the LIBSVM-style data format, included heart_scale example, solver selection, cross validation, and parameter search.
Why package nerds care
LIBLINEAR is package-nerd catnip because it is a small, fast C/C++ implementation of a heavily cited ML method with stable Unix-style tools. It is the kind of dependency that appears behind higher-level language bindings while still remaining useful as a direct CLI package.
Timeline
- 2008: LIBLINEAR paper submitted in May and published in JMLR in August.
- 2014: Public GitHub mirror created on May 19, 2014.
- 2022: NTU-hosted LIBLINEAR paper PDF marked last modified on March 5, 2022.
- 2025: GitHub repository metadata recorded push activity on December 29, 2025.
Related projects
- LIBSVM is the closest related project and the source of much of the package style, data-format familiarity, and user workflow.
- scikit-learn exposes LIBLINEAR as a solver option in LogisticRegression, carrying the implementation into the Python scientific ecosystem.
Sources
- https://api.github.com/repos/cjlin1/liblinear
- https://github.com/cjlin1/liblinear
- https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
- https://www.csie.ntu.edu.tw/~cjlin/liblinear/
- https://www.csie.ntu.edu.tw/~cjlin/papers/liblinear.pdf
- https://www.jmlr.org/papers/v9/fan08a.html
security posture
Risk level: green
library-like package without higher-risk signals.
Risk classifier
green risk · low confidence · appliance
Why
- library-like package without higher-risk signals
Signals
- metadata:library-like
Install behavior
- No Homebrew bottle metadata was recorded.
Recommended review
Before unattended agent use, check whether the tool reads plaintext credentials, writes remote state, publishes artifacts, or shells out to plugins.
executables
Installed executables
| Command | Kind | Exposure | Note |
|---|---|---|---|
predict | executable | indexed executable | Discovered from the local executable index. |
train | executable | indexed executable | Discovered from the local executable index. |
freshness
Version and freshness
These signals separate page generation age, package-manager activity, and upstream release comparison. Version lag is warned only when an evidence URL and comparable versions are present.
page generated2026-08-03
manager version2.50
manager updated
local dataunknown
upstreamnot available
latest detectednot detected
- okNo freshness warnings were generated.
install metadata
Package metadata
| Package key | brew:liblinear |
|---|---|
| Version | 2.50 |
| Package manager | Homebrew |
| Homepage | https://www.csie.ntu.edu.tw/~cjlin/liblinear/ |
| Repository | https://github.com/cjlin1/liblinear |
| Bottle | not recorded |
| Service | none declared |
source trail
Generated from repository data
This page is generated by av-web from the private package SQLite artifact built by scripts/generate-pkg-sqlite.py.
Combined YAML source
View the package source record on GitHub.
Used sources
- Geiger risk classifier
- Nucleus package database
- curated package history
- pkgdb category and tag curation