Actions
  • shareshare
  • link
  • cite
  • add
add
auto_awesome_motion View all 4 versions
Publication . Conference object . Article . Preprint . 2018

ensmallen: a flexible C++ library for efficient function optimization

Bhardwaj, Shikhar; Curtin, Ryan R.; Edel, Marcus; Mentekidis, Yannis; Sanderson, Conrad;
Open Access
English
Abstract
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.
Published in: Workshop on Systems for ML and Open Source Software at NIPS / NeurIPS, 2018. http://learningsys.org/nips18/
Subjects

Computer Science - Mathematical Software, Computer Science - Machine Learning, Mathematics - Optimization and Control, 65K10, 68N99, 68W99, 90C53, G.1.6, G.4, Mathematical Software (cs.MS), Machine Learning (cs.LG), Optimization and Control (math.OC), FOS: Computer and information sciences, FOS: Mathematics

36 references, page 1 of 4

[1] M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467, 2016.

[2] D. Abrahams and A. Gurtovoy. C++ Template Metaprogramming: Concepts, Tools, and Techniques from Boost and Beyond. Addison-Wesley Professional, 2004.

[3] R. K. Belew, J. McInerney, and N. N. Schraudolph. Evolving networks: Using the genetic algorithm with connectionist learning, 1990. CSE Technical Report #CS90-174, University of California at San Diego.

[4] F. Chollet. Keras. https://github.com/fchollet/keras, 2015.

[5] R. R. Curtin, M. Edel, M. Lozhnikov, Y. Mentekidis, S. Ghaisas, and S. Zhang. mlpack 3: a fast, flexible machine learning library. Journal of Open Source Software, 3:726, 2018.

[6] J. Duchi, E. Hazan, and Y. Singer. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12:2121-2159, 2011.

[7] J. W. Eaton, D. Bateman, S. Hauberg, and R. Wehbring. GNU Octave version 4.4.0 manual: a high-level interactive language for numerical computations, 2018.

[8] M. Frank and P. Wolfe. An algorithm for quadratic programming. Naval Research Logistics Quarterly, 3(1-2):95-110, 1956.

[9] N. Hansen and A. Ostermeier. Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation, 9(2):159-195, 2001.

[10] M. R. Hestenes. Multiplier and gradient methods. Journal of Optimization Theory and Applications, 4(5):303-320, 1969.

Related to Research communities
Social Science and Humanities
Download fromView all 4 sources
lock_open
moresidebar