Conference paper Open Access

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

Bhardwaj, Shikhar; Curtin, Ryan R.; Edel, Marcus; Mentekidis, Yannis; Sanderson, Conrad

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="" xmlns="" xsi:schemaLocation="">
  <identifier identifierType="DOI">10.5281/zenodo.2008651</identifier>
      <creatorName>Bhardwaj, Shikhar</creatorName>
      <creatorName>Curtin, Ryan R.</creatorName>
      <givenName>Ryan R.</givenName>
      <creatorName>Edel, Marcus</creatorName>
      <creatorName>Mentekidis, Yannis</creatorName>
      <creatorName>Sanderson, Conrad</creatorName>
    <title>ensmallen: a flexible C++ library for efficient function optimization</title>
    <date dateType="Issued">2018-12-07</date>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
    <alternateIdentifier alternateIdentifierType="url"></alternateIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.2008650</relatedIdentifier>
    <rights rightsURI="">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
    <description descriptionType="Abstract">&lt;p&gt;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.&lt;/p&gt;

    <description descriptionType="Other">Published in: Workshop on Systems for ML and Open Source Software at NIPS / NeurIPS, 2018.</description>
All versions This version
Views 510512
Downloads 153153
Data volume 50.7 MB50.7 MB
Unique views 485487
Unique downloads 143143


Cite as