ensmallen (C++ library)
1.11 / November 28, 2018
|License||BSD 3-clause (open source)|
ensmallen is a library of mathematical optimization algorithms for the C++ programming language. It provides a simple set of abstractions for writing an objective function to optimize. It also provides a large set of optimizers that can be used for virtually any mathematical optimization task. These include full-batch gradient descent techniques, small-batch techniques, gradient-free optimizers, and constrained optimization.
ensmallen is used by the mlpack library as an aid in the implementation of many of machine learning algorithms.
Available Optimizers[edit | edit source]
- many forms of stochastic gradient descent (including AdaGrad, RMSProp, Adam)
- many forms of Quasi-Newton methods (including L-BFGS and Augmented Lagrangian method)
- Conditional gradient descent
- Frank–Wolfe algorithm
- Simulated annealing
- Grid search
See also[edit | edit source]
Others articles of the Topic Free and open-source software : Gede (software), Grav (CMS), Shampoo (software), herbstluftwm, PageCarton, Wikimedia Foundation, Apache Commons DbUtils
Some use of "" in your query was not closed by a matching "".Some use of "" in your query was not closed by a matching "".
- List of optimization software
- List of numerical analysis software
- List of numerical libraries
- Numerical linear algebra
- Scientific computing
References[edit | edit source]
- "ensmallen documentation / changelog". Retrieved 12 December 2018.
- Shikhar Bhardwaj, Ryan R. Curtin, Yannis Mentekidis, Marcus Edel, Conrad Sanderson (2018). ensmallen: a flexible C++ library for efficient function optimization. Workshop on Systems for ML and Open Source Software at NIPS / NeurIPS. doi:10.5281/zenodo.2008650.CS1 maint: Multiple names: authors list (link)
[edit | edit source]
This article "Ensmallen (C++ library)" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Ensmallen (C++ library). Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.