The ensmallen library for flexible numerical optimization

We overview the ensmallen numerical optimization library, which provides a flexible C++ framework for mathematical optimization of user-supplied objective functions. Many types of objective functions are supported, including general, differentiable, separable, con-strained, and categorical. A diverse set of pre-built optimizers is provided, including Quasi-Newton optimizers and many variants of Stochastic Gradient Descent. The underlying framework facilitates the implementation of new optimizers. Optimization of an objective function typically requires supplying only one or two C++ functions. Custom behavior can be easily specified via callback functions. Empirical comparisons show that ensmallen outperforms other frameworks while providing more functionality. The library is available at https://ensmallen.org and is distributed under the permissive BSD license.

Automated summary

The ensmallen library provides a flexible C++ framework for numerical optimization of various objective functions, supporting a diverse range of pre-built optimizers. It is easy to implement new optimizers with its underlying framework. Empirical comparisons show that ensmallen outperforms other frameworks in terms of performance and functionality.