Awesome Open Source
Awesome Open Source

ensmallen: a C++ header-only library for numerical optimization

ensmallen is a C++ header-only library for numerical optimization.

Documentation and downloads:

ensmallen provides a simple set of abstractions for writing an objective function to optimize. It also provides a large set of standard and cutting-edge optimizers that can be used for virtually any numerical optimization task. These include full-batch gradient descent techniques, small-batch techniques, gradient-free optimizers, and constrained optimization.


  • C++ compiler with C++11 support
  • Armadillo:
  • OpenBLAS or Intel MKL or LAPACK (see Armadillo site for details)


ensmallen can be installed with CMake 3.3 or later. If CMake is not already available on your system, it can be obtained from

If you are using an older system such as RHEL 7 or CentOS 7, an updated version of CMake is also available via the EPEL repository via the cmake3 package.

Example installation:

mkdir build
cd build
cmake ..
sudo make install

Example Usage

See example.cpp for example usage of the L-BFGS optimizer in a linear regression setting.


Unless stated otherwise, the source code for ensmallen is licensed under the 3-clause BSD license (the "License"). A copy of the License is included in the "LICENSE.txt" file. You may also obtain a copy of the License at .


Please cite the following paper if you use ensmallen in your research and/or software. Citations are useful for the continued development and maintenance of the library.

  author    = {Shikhar Bhardwaj and
               Ryan R. Curtin and
               Marcus Edel and
               Yannis Mentekidis and
               Conrad Sanderson},
  title     = {ensmallen: a flexible {C++} library for efficient function optimization},
  journal   = {CoRR},
  volume    = {abs/1810.09361},
  doi       = {10.5281/zenodo.2008650},
  year      = {2018},
  url       = {},
  archivePrefix = {arXiv},
  eprint    = {1810.09361},
  timestamp = {Wed, 31 Oct 2018 14:24:29 +0100},
  biburl    = {},
  bibsource = {dblp computer science bibliography,}

Developers and Contributors

  • Ryan Curtin
  • Dongryeol Lee
  • Marcus Edel
  • Sumedh Ghaisas
  • Siddharth Agrawal
  • Stephen Tu
  • Shikhar Bhardwaj
  • Vivek Pal
  • Sourabh Varshney
  • Chenzhe Diao
  • Abhinav Moudgil
  • Konstantin Sidorov
  • Kirill Mishchenko
  • Kartik Nighania
  • Haritha Nair
  • Moksh Jain
  • Abhishek Laddha
  • Arun Reddy
  • Nishant Mehta
  • Trironk Kiatkungwanglai
  • Vasanth Kalingeri
  • Zhihao Lou
  • Conrad Sanderson
  • Dan Timson
  • N Rajiv Vaidyanathan
  • Roberto Hueso
  • Sayan Goswami

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
c-plus-plus (18,727
deep-learning (3,976
machine-learning (3,631
optimization (293
optimization-algorithms (39