CPT: Efficient Deep Neural Network Training via Cyclic Precision Article Swipe

PDF

Yonggan Fu , Han Guo , Meng Li , Xin Yang , Yining Ding , Vikas Chandra , Yingyan Lin ·

YOU? · · 2021 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2101.09868

Low-precision deep neural network (DNN) training has gained tremendous attention as reducing precision is one of the most effective knobs for boosting DNNs' training time/energy efficiency. In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training. Specifically, we propose Cyclic Precision Training (CPT) to cyclically vary the precision between two boundary values which can be identified using a simple precision range test within the first few training epochs. Extensive simulations and ablation studies on five datasets and eleven models demonstrate that CPT's effectiveness is consistent across various models/tasks (including classification and language modeling). Furthermore, through experiments and visualization we show that CPT helps to (1) converge to a wider minima with a lower generalization error and (2) reduce training variance which we believe opens up a new design knob for simultaneously improving the optimization and efficiency of DNN training. Our codes are available at: https://github.com/RICE-EIC/CPT.

Related Topics

Computer Science

Boosting (Machine Learning)

Artificial Intelligence

Perspective (Graphical)

Mathematical Analysis

Composite Material

Materials Science

Concepts

Computer science Boosting (machine learning) Artificial neural network Artificial intelligence Perspective (graphical) Deep neural networks Maxima and minima Machine learning Training (meteorology) Range (aeronautics) Generalization Mathematics Physics Meteorology Mathematical analysis Composite material Materials science

Metadata

Type: article
Language: en
Landing Page: http://arxiv.org/abs/2101.09868
PDF: https://arxiv.org/pdf/2101.09868
OA Status: green
Cited By: 11
References: 57
Related Works: 20
OpenAlex ID: https://openalex.org/W3120444801

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W3120444801

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2101.09868

Digital Object Identifier
Title: CPT: Efficient Deep Neural Network Training via Cyclic Precision

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2021

Year of publication
Publication date: 2021-01-25

Full publication date if available
Authors: Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin

List of authors in order
Landing page: https://arxiv.org/abs/2101.09868

Publisher landing page
PDF URL: https://arxiv.org/pdf/2101.09868

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2101.09868

Direct OA link when available
Concepts: Computer science, Boosting (machine learning), Artificial neural network, Artificial intelligence, Perspective (graphical), Deep neural networks, Maxima and minima, Machine learning, Training (meteorology), Range (aeronautics), Generalization, Mathematics, Physics, Meteorology, Mathematical analysis, Composite material, Materials science

Top concepts (fields/topics) attached by OpenAlex
Cited by: 11

Total citation count in OpenAlex
Citations by year (recent): 2025: 1, 2024: 2, 2023: 4, 2022: 1, 2021: 3

Per-year citation counts (last 5 years)
References (count): 57

Number of works referenced by this work
Related works (count): 20

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W3120444801
doi	https://doi.org/10.48550/arxiv.2101.09868
ids.doi	https://doi.org/10.48550/arxiv.2101.09868
ids.mag	3120444801
ids.openalex	https://openalex.org/W3120444801
fwci
type	article
title	CPT: Efficient Deep Neural Network Training via Cyclic Precision
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T12535
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9977999925613403
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Machine Learning and Data Classification
topics[1].id	https://openalex.org/T11307
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9973999857902527
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Domain Adaptation and Few-Shot Learning
topics[2].id	https://openalex.org/T10036
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9973999857902527
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1707
topics[2].subfield.display_name	Computer Vision and Pattern Recognition
topics[2].display_name	Advanced Neural Network Applications
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.8060577511787415
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C46686674
concepts[1].level	2
concepts[1].score	0.6441199779510498
concepts[1].wikidata	https://www.wikidata.org/wiki/Q466303
concepts[1].display_name	Boosting (machine learning)
concepts[2].id	https://openalex.org/C50644808
concepts[2].level	2
concepts[2].score	0.6121824383735657
concepts[2].wikidata	https://www.wikidata.org/wiki/Q192776
concepts[2].display_name	Artificial neural network
concepts[3].id	https://openalex.org/C154945302
concepts[3].level	1
concepts[3].score	0.5436550378799438
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[3].display_name	Artificial intelligence
concepts[4].id	https://openalex.org/C12713177
concepts[4].level	2
concepts[4].score	0.5196098685264587
concepts[4].wikidata	https://www.wikidata.org/wiki/Q1900281
concepts[4].display_name	Perspective (graphical)
concepts[5].id	https://openalex.org/C2984842247
concepts[5].level	3
concepts[5].score	0.5158704519271851
concepts[5].wikidata	https://www.wikidata.org/wiki/Q197536
concepts[5].display_name	Deep neural networks
concepts[6].id	https://openalex.org/C186633575
concepts[6].level	2
concepts[6].score	0.48833462595939636
concepts[6].wikidata	https://www.wikidata.org/wiki/Q845060
concepts[6].display_name	Maxima and minima
concepts[7].id	https://openalex.org/C119857082
concepts[7].level	1
concepts[7].score	0.4858967661857605
concepts[7].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[7].display_name	Machine learning
concepts[8].id	https://openalex.org/C2777211547
concepts[8].level	2
concepts[8].score	0.48263460397720337
concepts[8].wikidata	https://www.wikidata.org/wiki/Q17141490
concepts[8].display_name	Training (meteorology)
concepts[9].id	https://openalex.org/C204323151
concepts[9].level	2
concepts[9].score	0.46362924575805664
concepts[9].wikidata	https://www.wikidata.org/wiki/Q905424
concepts[9].display_name	Range (aeronautics)
concepts[10].id	https://openalex.org/C177148314
concepts[10].level	2
concepts[10].score	0.433709979057312
concepts[10].wikidata	https://www.wikidata.org/wiki/Q170084
concepts[10].display_name	Generalization
concepts[11].id	https://openalex.org/C33923547
concepts[11].level	0
concepts[11].score	0.09401527047157288
concepts[11].wikidata	https://www.wikidata.org/wiki/Q395
concepts[11].display_name	Mathematics
concepts[12].id	https://openalex.org/C121332964
concepts[12].level	0
concepts[12].score	0.0
concepts[12].wikidata	https://www.wikidata.org/wiki/Q413
concepts[12].display_name	Physics
concepts[13].id	https://openalex.org/C153294291
concepts[13].level	1
concepts[13].score	0.0
concepts[13].wikidata	https://www.wikidata.org/wiki/Q25261
concepts[13].display_name	Meteorology
concepts[14].id	https://openalex.org/C134306372
concepts[14].level	1
concepts[14].score	0.0
concepts[14].wikidata	https://www.wikidata.org/wiki/Q7754
concepts[14].display_name	Mathematical analysis
concepts[15].id	https://openalex.org/C159985019
concepts[15].level	1
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q181790
concepts[15].display_name	Composite material
concepts[16].id	https://openalex.org/C192562407
concepts[16].level	0
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q228736
concepts[16].display_name	Materials science
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.8060577511787415
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/boosting
keywords[1].score	0.6441199779510498
keywords[1].display_name	Boosting (machine learning)
keywords[2].id	https://openalex.org/keywords/artificial-neural-network
keywords[2].score	0.6121824383735657
keywords[2].display_name	Artificial neural network
keywords[3].id	https://openalex.org/keywords/artificial-intelligence
keywords[3].score	0.5436550378799438
keywords[3].display_name	Artificial intelligence
keywords[4].id	https://openalex.org/keywords/perspective
keywords[4].score	0.5196098685264587
keywords[4].display_name	Perspective (graphical)
keywords[5].id	https://openalex.org/keywords/deep-neural-networks
keywords[5].score	0.5158704519271851
keywords[5].display_name	Deep neural networks
keywords[6].id	https://openalex.org/keywords/maxima-and-minima
keywords[6].score	0.48833462595939636
keywords[6].display_name	Maxima and minima
keywords[7].id	https://openalex.org/keywords/machine-learning
keywords[7].score	0.4858967661857605
keywords[7].display_name	Machine learning
keywords[8].id	https://openalex.org/keywords/training
keywords[8].score	0.48263460397720337
keywords[8].display_name	Training (meteorology)
keywords[9].id	https://openalex.org/keywords/range
keywords[9].score	0.46362924575805664
keywords[9].display_name	Range (aeronautics)
keywords[10].id	https://openalex.org/keywords/generalization
keywords[10].score	0.433709979057312
keywords[10].display_name	Generalization
keywords[11].id	https://openalex.org/keywords/mathematics
keywords[11].score	0.09401527047157288
keywords[11].display_name	Mathematics
language	en
locations[0].id	pmh:oai:arXiv.org:2101.09868
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2101.09868
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2101.09868
locations[1].id	doi:10.48550/arxiv.2101.09868
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2101.09868
locations[2].id	mag:3120444801
locations[2].is_oa	False
locations[2].source.id	https://openalex.org/S4306419637
locations[2].source.issn
locations[2].source.type	conference
locations[2].source.is_oa	False
locations[2].source.issn_l
locations[2].source.is_core	False
locations[2].source.is_in_doaj	False
locations[2].source.display_name	International Conference on Learning Representations
locations[2].source.host_organization
locations[2].source.host_organization_name
locations[2].license
locations[2].pdf_url
locations[2].version
locations[2].raw_type
locations[2].license_id
locations[2].is_accepted	False
locations[2].is_published
locations[2].raw_source_name	International Conference on Learning Representations
locations[2].landing_page_url	https://openreview.net/pdf?id=87ZwsaQNHPZ
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5061572132
authorships[0].author.orcid	https://orcid.org/0000-0002-7483-2921
authorships[0].author.display_name	Yonggan Fu
authorships[0].countries	US
authorships[0].affiliations[0].institution_ids	https://openalex.org/I74775410
authorships[0].affiliations[0].raw_affiliation_string	Rice Univ
authorships[0].institutions[0].id	https://openalex.org/I74775410
authorships[0].institutions[0].ror	https://ror.org/008zs3103
authorships[0].institutions[0].type	education
authorships[0].institutions[0].lineage	https://openalex.org/I74775410
authorships[0].institutions[0].country_code	US
authorships[0].institutions[0].display_name	Rice University
authorships[0].author_position	first
authorships[0].raw_author_name	Yonggan Fu
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	Rice Univ
authorships[1].author.id	https://openalex.org/A5041591669
authorships[1].author.orcid	https://orcid.org/0000-0003-4257-8110
authorships[1].author.display_name	Han Guo
authorships[1].countries	US
authorships[1].affiliations[0].institution_ids	https://openalex.org/I74775410
authorships[1].affiliations[0].raw_affiliation_string	Rice Univ
authorships[1].institutions[0].id	https://openalex.org/I74775410
authorships[1].institutions[0].ror	https://ror.org/008zs3103
authorships[1].institutions[0].type	education
authorships[1].institutions[0].lineage	https://openalex.org/I74775410
authorships[1].institutions[0].country_code	US
authorships[1].institutions[0].display_name	Rice University
authorships[1].author_position	middle
authorships[1].raw_author_name	Han Guo
authorships[1].is_corresponding	False
authorships[1].raw_affiliation_strings	Rice Univ
authorships[2].author.id	https://openalex.org/A5100457556
authorships[2].author.orcid	https://orcid.org/0000-0003-2123-2444
authorships[2].author.display_name	Meng Li
authorships[2].countries	IL
authorships[2].affiliations[0].institution_ids	https://openalex.org/I2252078561
authorships[2].affiliations[0].raw_affiliation_string	Facebook
authorships[2].institutions[0].id	https://openalex.org/I2252078561
authorships[2].institutions[0].ror	https://ror.org/02388em19
authorships[2].institutions[0].type	company
authorships[2].institutions[0].lineage	https://openalex.org/I2252078561, https://openalex.org/I4210114444
authorships[2].institutions[0].country_code	IL
authorships[2].institutions[0].display_name	Meta (Israel)
authorships[2].author_position	middle
authorships[2].raw_author_name	Meng Li
authorships[2].is_corresponding	False
authorships[2].raw_affiliation_strings	Facebook
authorships[3].author.id	https://openalex.org/A5066153744
authorships[3].author.orcid	https://orcid.org/0000-0003-3431-5118
authorships[3].author.display_name	Xin Yang
authorships[3].countries	US
authorships[3].affiliations[0].institution_ids	https://openalex.org/I74775410
authorships[3].affiliations[0].raw_affiliation_string	Rice Univ
authorships[3].institutions[0].id	https://openalex.org/I74775410
authorships[3].institutions[0].ror	https://ror.org/008zs3103
authorships[3].institutions[0].type	education
authorships[3].institutions[0].lineage	https://openalex.org/I74775410
authorships[3].institutions[0].country_code	US
authorships[3].institutions[0].display_name	Rice University
authorships[3].author_position	middle
authorships[3].raw_author_name	Xin Yang
authorships[3].is_corresponding	False
authorships[3].raw_affiliation_strings	Rice Univ
authorships[4].author.id	https://openalex.org/A5008027618
authorships[4].author.orcid
authorships[4].author.display_name	Yining Ding
authorships[4].countries	US
authorships[4].affiliations[0].institution_ids	https://openalex.org/I74775410
authorships[4].affiliations[0].raw_affiliation_string	Rice Univ
authorships[4].institutions[0].id	https://openalex.org/I74775410
authorships[4].institutions[0].ror	https://ror.org/008zs3103
authorships[4].institutions[0].type	education
authorships[4].institutions[0].lineage	https://openalex.org/I74775410
authorships[4].institutions[0].country_code	US
authorships[4].institutions[0].display_name	Rice University
authorships[4].author_position	middle
authorships[4].raw_author_name	Yining Ding
authorships[4].is_corresponding	False
authorships[4].raw_affiliation_strings	Rice Univ
authorships[5].author.id	https://openalex.org/A5016704219
authorships[5].author.orcid	https://orcid.org/0009-0005-4996-8455
authorships[5].author.display_name	Vikas Chandra
authorships[5].countries	IL
authorships[5].affiliations[0].institution_ids	https://openalex.org/I2252078561
authorships[5].affiliations[0].raw_affiliation_string	Facebook
authorships[5].institutions[0].id	https://openalex.org/I2252078561
authorships[5].institutions[0].ror	https://ror.org/02388em19
authorships[5].institutions[0].type	company
authorships[5].institutions[0].lineage	https://openalex.org/I2252078561, https://openalex.org/I4210114444
authorships[5].institutions[0].country_code	IL
authorships[5].institutions[0].display_name	Meta (Israel)
authorships[5].author_position	middle
authorships[5].raw_author_name	Vikas Chandra
authorships[5].is_corresponding	False
authorships[5].raw_affiliation_strings	Facebook
authorships[6].author.id	https://openalex.org/A5019582323
authorships[6].author.orcid	https://orcid.org/0000-0001-5946-203X
authorships[6].author.display_name	Yingyan Lin
authorships[6].countries	US
authorships[6].affiliations[0].institution_ids	https://openalex.org/I74775410
authorships[6].affiliations[0].raw_affiliation_string	Rice Univ
authorships[6].institutions[0].id	https://openalex.org/I74775410
authorships[6].institutions[0].ror	https://ror.org/008zs3103
authorships[6].institutions[0].type	education
authorships[6].institutions[0].lineage	https://openalex.org/I74775410
authorships[6].institutions[0].country_code	US
authorships[6].institutions[0].display_name	Rice University
authorships[6].author_position	last
authorships[6].raw_author_name	Yingyan Lin
authorships[6].is_corresponding	False
authorships[6].raw_affiliation_strings	Rice Univ
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2101.09868
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	CPT: Efficient Deep Neural Network Training via Cyclic Precision
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T12535
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9977999925613403
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Machine Learning and Data Classification
related_works	https://openalex.org/W3125482586, https://openalex.org/W2972304044, https://openalex.org/W2755396225, https://openalex.org/W2903047678, https://openalex.org/W2887630004, https://openalex.org/W3113386868, https://openalex.org/W2965944882, https://openalex.org/W3205859423, https://openalex.org/W2970821029, https://openalex.org/W2982195460, https://openalex.org/W3016829100, https://openalex.org/W2972417230, https://openalex.org/W2763600295, https://openalex.org/W2908666743, https://openalex.org/W3006769269, https://openalex.org/W2949081261, https://openalex.org/W3129186946, https://openalex.org/W2931737270, https://openalex.org/W2802855137, https://openalex.org/W2752721426
cited_by_count	11
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	2
counts_by_year[2].year	2023
counts_by_year[2].cited_by_count	4
counts_by_year[3].year	2022
counts_by_year[3].cited_by_count	1
counts_by_year[4].year	2021
counts_by_year[4].cited_by_count	3
locations_count	3
best_oa_location.id	pmh:oai:arXiv.org:2101.09868
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2101.09868
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2101.09868
primary_location.id	pmh:oai:arXiv.org:2101.09868
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2101.09868
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2101.09868
publication_date	2021-01-25
publication_year	2021
referenced_works	https://openalex.org/W2970821029, https://openalex.org/W2963273111, https://openalex.org/W3106655949, https://openalex.org/W2469490737, https://openalex.org/W2914483840, https://openalex.org/W2769312802, https://openalex.org/W2751477244, https://openalex.org/W2407022425, https://openalex.org/W2963631907, https://openalex.org/W2194775991, https://openalex.org/W2982479999, https://openalex.org/W1632114991, https://openalex.org/W3118608800, https://openalex.org/W2963403868, https://openalex.org/W2999599167, https://openalex.org/W2963664311, https://openalex.org/W2963163009, https://openalex.org/W2300242332, https://openalex.org/W3040551860, https://openalex.org/W2525332836, https://openalex.org/W2964054038, https://openalex.org/W3035232708, https://openalex.org/W2860338957, https://openalex.org/W3040522390, https://openalex.org/W2743945814, https://openalex.org/W2748818695, https://openalex.org/W2963709416, https://openalex.org/W2108598243, https://openalex.org/W2064675550, https://openalex.org/W3099584108, https://openalex.org/W2963374099, https://openalex.org/W2990765879, https://openalex.org/W3035183452, https://openalex.org/W2889797931, https://openalex.org/W2997760144, https://openalex.org/W2970388773, https://openalex.org/W2995197005, https://openalex.org/W2897097528, https://openalex.org/W2319920447, https://openalex.org/W2518108298, https://openalex.org/W2916954108, https://openalex.org/W2804193803, https://openalex.org/W2560017826, https://openalex.org/W3042701997, https://openalex.org/W2963393494, https://openalex.org/W1964929969, https://openalex.org/W2963114950, https://openalex.org/W2902036584, https://openalex.org/W2962933129, https://openalex.org/W2963112338, https://openalex.org/W2405920868, https://openalex.org/W2647836899, https://openalex.org/W2786098160, https://openalex.org/W2970233825, https://openalex.org/W2263490141, https://openalex.org/W2964004663, https://openalex.org/W2963480671
referenced_works_count	57
abstract_inverted_index.a	36, 55, 103, 153, 157, 171
abstract_inverted_index.In	26
abstract_inverted_index.as	10, 39, 58
abstract_inverted_index.be	100
abstract_inverted_index.by	41
abstract_inverted_index.in	44
abstract_inverted_index.is	13, 129
abstract_inverted_index.of	15, 79, 182
abstract_inverted_index.on	119
abstract_inverted_index.to	31, 89, 149, 152
abstract_inverted_index.up	170
abstract_inverted_index.we	29, 48, 83, 144, 167
abstract_inverted_index.(1)	150
abstract_inverted_index.(2)	162
abstract_inverted_index.CPT	147
abstract_inverted_index.DNN	46, 63, 80, 183
abstract_inverted_index.Our	185
abstract_inverted_index.and	65, 116, 122, 136, 142, 161, 180
abstract_inverted_index.are	187
abstract_inverted_index.at:	189
abstract_inverted_index.can	99
abstract_inverted_index.few	111
abstract_inverted_index.for	20, 73, 175
abstract_inverted_index.has	6
abstract_inverted_index.new	37, 172
abstract_inverted_index.one	14
abstract_inverted_index.the	16, 59, 70, 76, 92, 109, 178
abstract_inverted_index.two	95
abstract_inverted_index.deep	1
abstract_inverted_index.five	120
abstract_inverted_index.from	35
abstract_inverted_index.have	54
abstract_inverted_index.knob	174
abstract_inverted_index.most	17
abstract_inverted_index.rate	61
abstract_inverted_index.show	145
abstract_inverted_index.test	107
abstract_inverted_index.that	50, 126, 146
abstract_inverted_index.this	27
abstract_inverted_index.vary	91
abstract_inverted_index.with	156
abstract_inverted_index.(CPT)	88
abstract_inverted_index.(DNN)	4
abstract_inverted_index.CPT's	127
abstract_inverted_index.DNNs'	22, 51
abstract_inverted_index.along	69
abstract_inverted_index.codes	186
abstract_inverted_index.error	160
abstract_inverted_index.first	110
abstract_inverted_index.helps	148
abstract_inverted_index.knobs	19
abstract_inverted_index.lower	158
abstract_inverted_index.might	53
abstract_inverted_index.opens	169
abstract_inverted_index.range	106
abstract_inverted_index.using	102
abstract_inverted_index.which	98, 166
abstract_inverted_index.wider	154
abstract_inverted_index.Cyclic	85
abstract_inverted_index.across	131
abstract_inverted_index.design	173
abstract_inverted_index.during	62
abstract_inverted_index.effect	57
abstract_inverted_index.eleven	123
abstract_inverted_index.gained	7
abstract_inverted_index.minima	155
abstract_inverted_index.models	124
abstract_inverted_index.neural	2
abstract_inverted_index.paper,	28
abstract_inverted_index.recent	42
abstract_inverted_index.reduce	163
abstract_inverted_index.simple	104
abstract_inverted_index.values	97
abstract_inverted_index.within	108
abstract_inverted_index.attempt	30
abstract_inverted_index.believe	168
abstract_inverted_index.between	94
abstract_inverted_index.dynamic	67
abstract_inverted_index.epochs.	113
abstract_inverted_index.explore	32
abstract_inverted_index.further	74
abstract_inverted_index.network	3
abstract_inverted_index.propose	84
abstract_inverted_index.similar	56
abstract_inverted_index.studies	118
abstract_inverted_index.through	140
abstract_inverted_index.various	132
abstract_inverted_index.Training	87
abstract_inverted_index.ablation	117
abstract_inverted_index.advocate	66
abstract_inverted_index.boosting	21, 75
abstract_inverted_index.boundary	96
abstract_inverted_index.converge	151
abstract_inverted_index.datasets	121
abstract_inverted_index.findings	43
abstract_inverted_index.inspired	40
abstract_inverted_index.language	137
abstract_inverted_index.learning	60
abstract_inverted_index.reducing	11
abstract_inverted_index.training	5, 23, 34, 71, 112, 164
abstract_inverted_index.variance	165
abstract_inverted_index.Extensive	114
abstract_inverted_index.Precision	86
abstract_inverted_index.attention	9
abstract_inverted_index.available	188
abstract_inverted_index.effective	18
abstract_inverted_index.improving	177
abstract_inverted_index.precision	12, 52, 68, 93, 105
abstract_inverted_index.training,	64
abstract_inverted_index.training.	81, 184
abstract_inverted_index.training:	47
abstract_inverted_index.(including	134
abstract_inverted_index.conjecture	49
abstract_inverted_index.consistent	130
abstract_inverted_index.cyclically	90
abstract_inverted_index.efficiency	78, 181
abstract_inverted_index.identified	101
abstract_inverted_index.modeling).	138
abstract_inverted_index.trajectory	72
abstract_inverted_index.tremendous	8
abstract_inverted_index.demonstrate	125
abstract_inverted_index.efficiency.	25
abstract_inverted_index.experiments	141
abstract_inverted_index.perspective	38
abstract_inverted_index.simulations	115
abstract_inverted_index.time/energy	24, 77
abstract_inverted_index.Furthermore,	139
abstract_inverted_index.models/tasks	133
abstract_inverted_index.optimization	179
abstract_inverted_index.Low-precision	0
abstract_inverted_index.Specifically,	82
abstract_inverted_index.effectiveness	128
abstract_inverted_index.low-precision	33
abstract_inverted_index.understanding	45
abstract_inverted_index.visualization	143
abstract_inverted_index.classification	135
abstract_inverted_index.generalization	159
abstract_inverted_index.simultaneously	176
abstract_inverted_index.https://github.com/RICE-EIC/CPT.	190
cited_by_percentile_year
countries_distinct_count	2
institutions_distinct_count	7
sustainable_development_goals[0].id	https://metadata.un.org/sdg/7
sustainable_development_goals[0].score	0.9100000262260437
sustainable_development_goals[0].display_name	Affordable and clean energy
citation_normalized_percentile