Corpus ID: 212633763

Flexible numerical optimization with ensmallen

@article{Curtin2020FlexibleNO,
  title={Flexible numerical optimization with ensmallen},
  author={Ryan R. Curtin and Marcus Edel and Rahul Ganesh Prabhu and Suryoday Basak and Zhihao Lou and Conrad Sanderson},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.04103}
}
  • Ryan R. Curtin, Marcus Edel, +3 authors Conrad Sanderson
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • This report provides an introduction to the ensmallen numerical optimization library, as well as a deep dive into the technical details of how it works. The library provides a fast and flexible C++ framework for mathematical optimization of arbitrary user-supplied functions. A large set of pre-built optimizers is provided, including many variants of Stochastic Gradient Descent and Quasi-Newton optimizers. Several types of objective functions are supported, including differentiable, separable… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 93 REFERENCES
    ensmallen: a flexible C++ library for efficient function optimization
    6
    Optim: A mathematical optimization package for Julia
    63
    Forward-Mode Automatic Differentiation in Julia
    84
    RBFOpt: an open-source library for black-box optimization with costly function evaluations
    59
    Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization
    721
    Adam: A Method for Stochastic Optimization
    46862
    Theano: A Python framework for fast computation of mathematical expressions
    1772
    Completely Derandomized Self-Adaptation in Evolution Strategies
    2884
    On the limited memory BFGS method for large scale optimization
    4755
    Katyusha: the first direct acceleration of stochastic gradient methods
    190