Scipediacontent: Scipediacontent moved page Draft Content 946365921 to Shasha et al 2020a

2021-01-28T20:08:54Z

Scipediacontent moved page Draft Content 946365921 to Shasha et al 2020a

Scipediacontent: Created page with " == Abstract == Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pip..."

2021-01-28T20:08:49Z

Created page with " == Abstract == Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pip..."

New page

== Abstract ==

Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous or uninformative outputs, the pipeline may fail or produce incorrect results. Inferring the root cause of failures and unexpected behavior is challenging, usually requiring much human thought, and is both time-consuming and error-prone. We propose a new approach that makes use of iteration and provenance to automatically infer the root causes and derive succinct explanations of failures. Through a detailed experimental evaluation, we assess the cost, precision, and recall of our approach compared to the state of the art. Our source code and experimental data will be available for reproducibility and enhancement.

Comment: 10 page

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/2002.04640 http://arxiv.org/abs/2002.04640]

* [http://arxiv.org/pdf/2002.04640 http://arxiv.org/pdf/2002.04640]

* [http://dl.acm.org/ft_gateway.cfm?id=3329489&ftid=2064725&dwn=1 http://dl.acm.org/ft_gateway.cfm?id=3329489&ftid=2064725&dwn=1],
: [http://dx.doi.org/10.1145/3329486.3329489 http://dx.doi.org/10.1145/3329486.3329489] under the license http://www.acm.org/publications/policies/copyright_policy#Background

* [https://dblp.uni-trier.de/db/journals/corr/corr2002.html#abs-2002-04640 https://dblp.uni-trier.de/db/journals/corr/corr2002.html#abs-2002-04640],
: [https://arxiv.org/abs/2002.04640 https://arxiv.org/abs/2002.04640],
: [https://dl.acm.org/citation.cfm?id=3329489 https://dl.acm.org/citation.cfm?id=3329489],
: [https://arxiv.org/pdf/2002.04640v1 https://arxiv.org/pdf/2002.04640v1],
: [https://nyuscholars.nyu.edu/en/publications/debugging-machine-learning-pipelines https://nyuscholars.nyu.edu/en/publications/debugging-machine-learning-pipelines],
: [https://doi.org/10.1145/3329486.3329489 https://doi.org/10.1145/3329486.3329489],
: [https://jp.arxiv.org/abs/2002.04640 https://jp.arxiv.org/abs/2002.04640],
: [https://za.arxiv.org/abs/2002.04640 https://za.arxiv.org/abs/2002.04640],
: [https://uk.arxiv.org/abs/2002.04640 https://uk.arxiv.org/abs/2002.04640],
: [https://it.arxiv.org/abs/2002.04640 https://it.arxiv.org/abs/2002.04640],
: [https://aps.arxiv.org/abs/2002.04640 https://aps.arxiv.org/abs/2002.04640],
: [https://academic.microsoft.com/#/detail/2948038809 https://academic.microsoft.com/#/detail/2948038809]

← Older revision	Revision as of 20:08, 28 January 2021
(No difference)

Shasha et al 2020a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 946365921 to Shasha et al 2020a

Scipediacontent: Created page with " == Abstract == Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pip..."