ensmallen: a flexible C++ library for efficient function optimization
This provides a fast and flexible tool for researchers and practitioners in machine learning to implement and prototype optimization algorithms, though it is incremental as it builds on existing optimization methods.
The authors tackled the problem of efficient function optimization in machine learning by developing ensmallen, a flexible C++ library that supports various optimization types and outperforms other frameworks like Julia and SciPy, sometimes by large margins.
We present ensmallen, a fast and flexible C++ library for mathematical optimization of arbitrary user-supplied functions, which can be applied to many machine learning problems. Several types of optimizations are supported, including differentiable, separable, constrained, and categorical objective functions. The library provides many pre-built optimizers (including numerous variants of SGD and Quasi-Newton optimizers) as well as a flexible framework for implementing new optimizers and objective functions. Implementation of a new optimizer requires only one method and a new objective function requires typically one or two C++ functions. This can aid in the quick implementation and prototyping of new machine learning algorithms. Due to the use of C++ template metaprogramming, ensmallen is able to support compiler optimizations that provide fast runtimes. Empirical comparisons show that ensmallen is able to outperform other optimization frameworks (like Julia and SciPy), sometimes by large margins. The library is distributed under the BSD license and is ready for use in production environments.