Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Creating pull request for 10.21105.joss.03076 #2804

Closed
wants to merge 2 commits into from
Closed

Creating pull request for 10.21105.joss.03076 #2804

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
efe721f
Creating 10.21105.joss.03076.pdf
whedon Dec 9, 2021
6127d12
Creating 10.21105.joss.03076.crossref.xml
whedon Dec 9, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
172 changes: 172 additions & 0 deletions joss.03076/10.21105.joss.03076.crossref.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,172 @@
<?xml version="1.0" encoding="UTF-8"?>
<doi_batch xmlns="http://www.crossref.org/schema/4.4.0" xmlns:ai="http://www.crossref.org/AccessIndicators.xsd" xmlns:rel="http://www.crossref.org/relations.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" version="4.4.0" xsi:schemaLocation="http://www.crossref.org/schema/4.4.0 http://www.crossref.org/schemas/crossref4.4.0.xsd">
<head>
<doi_batch_id>ab41759847420b66cd7217df56146a2f</doi_batch_id>
<timestamp>20211209144917</timestamp>
<depositor>
<depositor_name>JOSS Admin</depositor_name>
<email_address>[email protected]</email_address>
</depositor>
<registrant>The Open Journal</registrant>
</head>
<body>
<journal>
<journal_metadata>
<full_title>Journal of Open Source Software</full_title>
<abbrev_title>JOSS</abbrev_title>
<issn media_type="electronic">2475-9066</issn>
<doi_data>
<doi>10.21105/joss</doi>
<resource>https://joss.theoj.org</resource>
</doi_data>
</journal_metadata>
<journal_issue>
<publication_date media_type="online">
<month>12</month>
<year>2021</year>
</publication_date>
<journal_volume>
<volume>6</volume>
</journal_volume>
<issue>68</issue>
</journal_issue>
<journal_article publication_type="full_text">
<titles>
<title>MUQ: The MIT Uncertainty Quantification Library</title>
</titles>
<contributors>
<person_name sequence="first" contributor_role="author">
<given_name>Matthew</given_name>
<surname>Parno</surname>
<ORCID>http://orcid.org/0000-0002-9419-2693</ORCID>
</person_name>
<person_name sequence="additional" contributor_role="author">
<given_name>Andrew</given_name>
<surname>Davis</surname>
<ORCID>http://orcid.org/0000-0002-6023-0989</ORCID>
</person_name>
<person_name sequence="additional" contributor_role="author">
<given_name>Linus</given_name>
<surname>Seelinger</surname>
<ORCID>http://orcid.org/0000-0001-8632-8493</ORCID>
</person_name>
</contributors>
<publication_date>
<month>12</month>
<day>09</day>
<year>2021</year>
</publication_date>
<pages>
<first_page>3076</first_page>
</pages>
<publisher_item>
<identifier id_type="doi">10.21105/joss.03076</identifier>
</publisher_item>
<ai:program name="AccessIndicators">
<ai:license_ref applies_to="vor">http://creativecommons.org/licenses/by/4.0/</ai:license_ref>
<ai:license_ref applies_to="am">http://creativecommons.org/licenses/by/4.0/</ai:license_ref>
<ai:license_ref applies_to="tdm">http://creativecommons.org/licenses/by/4.0/</ai:license_ref>
</ai:program>
<rel:program>
<rel:related_item>
<rel:description>Software archive</rel:description>
<rel:inter_work_relation relationship-type="references" identifier-type="doi">“https://doi.org/10.5281/zenodo.5770267”</rel:inter_work_relation>
</rel:related_item>
<rel:related_item>
<rel:description>GitHub review issue</rel:description>
<rel:inter_work_relation relationship-type="hasReview" identifier-type="uri">https://github.com/openjournals/joss-reviews/issues/3076</rel:inter_work_relation>
</rel:related_item>
</rel:program>
<doi_data>
<doi>10.21105/joss.03076</doi>
<resource>https://joss.theoj.org/papers/10.21105/joss.03076</resource>
<collection property="text-mining">
<item>
<resource mime_type="application/pdf">https://joss.theoj.org/papers/10.21105/joss.03076.pdf</resource>
</item>
</collection>
</doi_data>
<citation_list>
<citation key="ref1">
<doi>10.7717/peerj-cs.55</doi>
</citation>
<citation key="ref2">
<doi>10.1016/j.jcp.2015.10.008</doi>
</citation>
<citation key="ref3">
<unstructured_citation>Johnson, Steven, The NLopt nonlinear-optimization package, http://github.com/stevengj/nlopt, 2007</unstructured_citation>
</citation>
<citation key="ref4">
<unstructured_citation>Guennebaud, Gaël and Jacob, Benoît and others, Eigen v3, http://eigen.tuxfamily.org, 2010</unstructured_citation>
</citation>
<citation key="ref5">
<unstructured_citation>nanoflann: a C++ header-only fork of FLANN, a library for Nearest Neighbor (NN) with KD-trees, Blanco, Jose Luis and Rai, Pranjal Kumar, https://github.com/jlblancoc/nanoflann, 2014</unstructured_citation>
</citation>
<citation key="ref6">
<doi>10.1145/1089014.1089020</doi>
</citation>
<citation key="ref7">
<unstructured_citation>Boost, 2015, Boost C++ Libraries, http://www.boost.org/</unstructured_citation>
</citation>
<citation key="ref8">
<doi>10.18637/jss.v076.i01</doi>
</citation>
<citation key="ref9">
<unstructured_citation>The Stan Math Library: Reverse-Mode Automatic Differentiation in C++, Carpenter, Bob and Hoffman, Matthew D. and Brubaker, Marcus and Lee, Daniel and Li, Peter and Betancourt, Michael, 2015, 1509.07164, arXiv, cs.MS, https://arxiv.org/abs/1509.07164</unstructured_citation>
</citation>
<citation key="ref10">
<unstructured_citation>tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware, Lao, Junpeng and Suter, Christopher and Langmore, Ian and Chimisov, Cyril and Saxena, Ashish and Sountsov, Pavel and Moore, Dave and Saurous, Rif A. and Hoffman, Matthew D. and Dillon, Joshua V., 2020, 2002.01184, arXiv, stat.CO, https://arxiv.org/abs/2002.01184</unstructured_citation>
</citation>
<citation key="ref11">
<doi>10.1002/sim.3680</doi>
</citation>
<citation key="ref12">
<unstructured_citation>JAGS: A program for analysis of Bayesian graphical models using Gibbs sampling, Plummer, Martyn and others, Proceedings of the 3rd international workshop on distributed statistical computing, 124, 125.10, 1–10, 2003, Vienna, Austria., https://www.r-project.org/conferences/DSC-2003/Proceedings/Plummer.pdf, https://www.r-project.org/conferences/DSC-2003/Proceedings/</unstructured_citation>
</citation>
<citation key="ref13">
<doi>10.1214/13-STS421</doi>
</citation>
<citation key="ref14">
<doi>10.1111/1467-9868.00294</doi>
</citation>
<citation key="ref15">
<doi>10.1615/Int.J.UncertaintyQuantification.2019027384</doi>
</citation>
<citation key="ref16">
<unstructured_citation>A Stein variational Newton method, Detommaso, Gianluca and Cui, Tiangang and Spantini, Alessio and Marzouk, Youssef and Scheichl, Robert, 2018, 1806.03085, arXiv, stat.ML, https://arxiv.org/abs/1806.03085</unstructured_citation>
</citation>
<citation key="ref17">
<unstructured_citation>Stein Variational Gradient Descent Without Gradient, Han, Jun and Liu, Qiang, Proceedings of the 35th International Conference on Machine Learning, 1900–1908, 2018, Dy, Jennifer and Krause, Andreas, 80, Proceedings of Machine Learning Research, 10–15 Jul, PMLR, http://proceedings.mlr.press/v80/han18b/han18b.pdf, https://proceedings.mlr.press/v80/han18b.html, Stein variational gradient decent (SVGD) has been shown to be a powerful approximate inference algorithm for complex distributions. However, the standard SVGD requires calculating the gradient of the target density and cannot be applied when the gradient is unavailable. In this work, we develop a gradient-free variant of SVGD (GF-SVGD), which replaces the true gradient with a surrogate gradient, and corrects the introduced bias by re-weighting the gradients in a proper form. We show that our GF-SVGD can be viewed as the standard SVGD with a special choice of kernel, and hence directly inherits all the theoretical properties of SVGD. We shed insights on the empirical choice of the surrogate gradient and further, propose an annealed GF-SVGD that consistently outperforms a number of recent advanced gradient-free MCMC methods in our empirical studies.</unstructured_citation>
</citation>
<citation key="ref18">
<doi>10.1137/130915005</doi>
</citation>
<citation key="ref19">
<doi>10.1137/19M126966X</doi>
</citation>
<citation key="ref20">
<doi>10.1137/120890715</doi>
</citation>
<citation key="ref21">
<doi>10.1137/16M1084080</doi>
</citation>
<citation key="ref22">
<unstructured_citation>Rate-optimal refinement strategies for local approximation MCMC, Davis, Andrew D. and Marzouk, Youssef and Smith, Aaron and Pillai, Natesh, 2021, 2006.00032, arXiv, stat.CO, https://arxiv.org/abs/2006.00032</unstructured_citation>
</citation>
<citation key="ref23">
<doi>10.1137/17M1134640</doi>
</citation>
<citation key="ref24">
<doi>10.1287/opre.1070.0496</doi>
</citation>
<citation key="ref25">
<unstructured_citation>Jakob, Wenzel and Rhinelander, Jason and Moldovan, Dean, 2017, https://github.com/pybind/pybind11, pybind11 – Seamless operability between C++11 and Python</unstructured_citation>
</citation>
<citation key="ref26">
<doi>10.1145/3458817.3476150</doi>
</citation>
</citation_list>
</journal_article>
</journal>
</body>
</doi_batch>
Binary file added joss.03076/10.21105.joss.03076.pdf
View file
Open in desktop
Binary file not shown.