---
_id: '14460'
abstract:
- lang: eng
text: We provide an efficient implementation of the backpropagation algorithm, specialized
to the case where the weights of the neural network being trained are sparse.
Our algorithm is general, as it applies to arbitrary (unstructured) sparsity and
common layer types (e.g., convolutional or linear). We provide a fast vectorized
implementation on commodity CPUs, and show that it can yield speedups in end-to-end
runtime experiments, both in transfer learning using already-sparsified networks,
and in training sparse networks from scratch. Thus, our results provide the first
support for sparse training on commodity hardware.
acknowledgement: 'We would like to thank Elias Frantar for his valuable assistance
and support at the outset of this project, and the anonymous ICML and SNN reviewers
for very constructive feedback. EI was supported in part by the FWF DK VGSCO, grant
agreement number W1260-N35. DA acknowledges generous ERC support, via Starting Grant
805223 ScaleML. '
alternative_title:
- PMLR
article_processing_charge: No
arxiv: 1
author:
- first_name: Mahdi
full_name: Nikdan, Mahdi
id: 66374281-f394-11eb-9cf6-869147deecc0
last_name: Nikdan
- first_name: Tommaso
full_name: Pegolotti, Tommaso
last_name: Pegolotti
- first_name: Eugenia B
full_name: Iofinova, Eugenia B
id: f9a17499-f6e0-11ea-865d-fdf9a3f77117
last_name: Iofinova
orcid: 0000-0002-7778-3221
- first_name: Eldar
full_name: Kurtic, Eldar
id: 47beb3a5-07b5-11eb-9b87-b108ec578218
last_name: Kurtic
- first_name: Dan-Adrian
full_name: Alistarh, Dan-Adrian
id: 4A899BFC-F248-11E8-B48F-1D18A9856A87
last_name: Alistarh
orcid: 0000-0003-3650-940X
citation:
ama: 'Nikdan M, Pegolotti T, Iofinova EB, Kurtic E, Alistarh D-A. SparseProp: Efficient
sparse backpropagation for faster training of neural networks at the edge. In:
Proceedings of the 40th International Conference on Machine Learning. Vol
202. ML Research Press; 2023:26215-26227.'
apa: 'Nikdan, M., Pegolotti, T., Iofinova, E. B., Kurtic, E., & Alistarh, D.-A.
(2023). SparseProp: Efficient sparse backpropagation for faster training of neural
networks at the edge. In Proceedings of the 40th International Conference on
Machine Learning (Vol. 202, pp. 26215–26227). Honolulu, Hawaii, HI, United
States: ML Research Press.'
chicago: 'Nikdan, Mahdi, Tommaso Pegolotti, Eugenia B Iofinova, Eldar Kurtic, and
Dan-Adrian Alistarh. “SparseProp: Efficient Sparse Backpropagation for Faster
Training of Neural Networks at the Edge.” In Proceedings of the 40th International
Conference on Machine Learning, 202:26215–27. ML Research Press, 2023.'
ieee: 'M. Nikdan, T. Pegolotti, E. B. Iofinova, E. Kurtic, and D.-A. Alistarh, “SparseProp:
Efficient sparse backpropagation for faster training of neural networks at the
edge,” in Proceedings of the 40th International Conference on Machine Learning,
Honolulu, Hawaii, HI, United States, 2023, vol. 202, pp. 26215–26227.'
ista: 'Nikdan M, Pegolotti T, Iofinova EB, Kurtic E, Alistarh D-A. 2023. SparseProp:
Efficient sparse backpropagation for faster training of neural networks at the
edge. Proceedings of the 40th International Conference on Machine Learning. ICML:
International Conference on Machine Learning, PMLR, vol. 202, 26215–26227.'
mla: 'Nikdan, Mahdi, et al. “SparseProp: Efficient Sparse Backpropagation for Faster
Training of Neural Networks at the Edge.” Proceedings of the 40th International
Conference on Machine Learning, vol. 202, ML Research Press, 2023, pp. 26215–27.'
short: M. Nikdan, T. Pegolotti, E.B. Iofinova, E. Kurtic, D.-A. Alistarh, in:, Proceedings
of the 40th International Conference on Machine Learning, ML Research Press, 2023,
pp. 26215–26227.
conference:
end_date: 2023-07-29
location: Honolulu, Hawaii, HI, United States
name: 'ICML: International Conference on Machine Learning'
start_date: 2023-07-23
date_created: 2023-10-29T23:01:17Z
date_published: 2023-07-30T00:00:00Z
date_updated: 2023-10-31T09:33:51Z
day: '30'
department:
- _id: DaAl
ec_funded: 1
external_id:
arxiv:
- '2302.04852'
intvolume: ' 202'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2302.04852
month: '07'
oa: 1
oa_version: Preprint
page: 26215-26227
project:
- _id: 268A44D6-B435-11E9-9278-68D0E5697425
call_identifier: H2020
grant_number: '805223'
name: Elastic Coordination for Scalable Machine Learning
publication: Proceedings of the 40th International Conference on Machine Learning
publication_identifier:
eissn:
- 2640-3498
publication_status: published
publisher: ML Research Press
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'SparseProp: Efficient sparse backpropagation for faster training of neural
networks at the edge'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 202
year: '2023'
...
---
_id: '14771'
abstract:
- lang: eng
text: Pruning—that is, setting a significant subset of the parameters of a neural
network to zero—is one of the most popular methods of model compression. Yet,
several recent works have raised the issue that pruning may induce or exacerbate
bias in the output of the compressed model. Despite existing evidence for this
phenomenon, the relationship between neural network pruning and induced bias is
not well-understood. In this work, we systematically investigate and characterize
this phenomenon in Convolutional Neural Networks for computer vision. First, we
show that it is in fact possible to obtain highly-sparse models, e.g. with less
than 10% remaining weights, which do not decrease in accuracy nor substantially
increase in bias when compared to dense models. At the same time, we also find
that, at higher sparsities, pruned models exhibit higher uncertainty in their
outputs, as well as increased correlations, which we directly link to increased
bias. We propose easy-to-use criteria which, based only on the uncompressed model,
establish whether bias will increase with pruning, and identify the samples most
susceptible to biased predictions post-compression. Our code can be found at https://github.com/IST-DASLab/pruned-vision-model-bias.
acknowledgement: The authors would like to sincerely thank Sara Hooker for her feedback
during the development of this work. EI was supported in part by the FWF DK VGSCO,
grant agreement number W1260-N35. AP and DA acknowledge generous ERC support, via
Starting Grant 805223 ScaleML.
article_processing_charge: No
arxiv: 1
author:
- first_name: Eugenia B
full_name: Iofinova, Eugenia B
id: f9a17499-f6e0-11ea-865d-fdf9a3f77117
last_name: Iofinova
orcid: 0000-0002-7778-3221
- first_name: Elena-Alexandra
full_name: Peste, Elena-Alexandra
id: 32D78294-F248-11E8-B48F-1D18A9856A87
last_name: Peste
- first_name: Dan-Adrian
full_name: Alistarh, Dan-Adrian
id: 4A899BFC-F248-11E8-B48F-1D18A9856A87
last_name: Alistarh
orcid: 0000-0003-3650-940X
citation:
ama: 'Iofinova EB, Peste E-A, Alistarh D-A. Bias in pruned vision models: In-depth
analysis and countermeasures. In: 2023 IEEE/CVF Conference on Computer Vision
and Pattern Recognition. IEEE; 2023:24364-24373. doi:10.1109/cvpr52729.2023.02334'
apa: 'Iofinova, E. B., Peste, E.-A., & Alistarh, D.-A. (2023). Bias in pruned
vision models: In-depth analysis and countermeasures. In 2023 IEEE/CVF Conference
on Computer Vision and Pattern Recognition (pp. 24364–24373). Vancouver, BC,
Canada: IEEE. https://doi.org/10.1109/cvpr52729.2023.02334'
chicago: 'Iofinova, Eugenia B, Elena-Alexandra Peste, and Dan-Adrian Alistarh. “Bias
in Pruned Vision Models: In-Depth Analysis and Countermeasures.” In 2023 IEEE/CVF
Conference on Computer Vision and Pattern Recognition, 24364–73. IEEE, 2023.
https://doi.org/10.1109/cvpr52729.2023.02334.'
ieee: 'E. B. Iofinova, E.-A. Peste, and D.-A. Alistarh, “Bias in pruned vision models:
In-depth analysis and countermeasures,” in 2023 IEEE/CVF Conference on Computer
Vision and Pattern Recognition, Vancouver, BC, Canada, 2023, pp. 24364–24373.'
ista: 'Iofinova EB, Peste E-A, Alistarh D-A. 2023. Bias in pruned vision models:
In-depth analysis and countermeasures. 2023 IEEE/CVF Conference on Computer Vision
and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition,
24364–24373.'
mla: 'Iofinova, Eugenia B., et al. “Bias in Pruned Vision Models: In-Depth Analysis
and Countermeasures.” 2023 IEEE/CVF Conference on Computer Vision and Pattern
Recognition, IEEE, 2023, pp. 24364–73, doi:10.1109/cvpr52729.2023.02334.'
short: E.B. Iofinova, E.-A. Peste, D.-A. Alistarh, in:, 2023 IEEE/CVF Conference
on Computer Vision and Pattern Recognition, IEEE, 2023, pp. 24364–24373.
conference:
end_date: 2023-06-24
location: Vancouver, BC, Canada
name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
start_date: 2023-06-17
date_created: 2024-01-10T08:42:40Z
date_published: 2023-08-22T00:00:00Z
date_updated: 2024-01-10T08:59:26Z
day: '22'
department:
- _id: DaAl
- _id: ChLa
doi: 10.1109/cvpr52729.2023.02334
ec_funded: 1
external_id:
arxiv:
- '2304.12622'
isi:
- '001062531308068'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2304.12622
month: '08'
oa: 1
oa_version: Preprint
page: 24364-24373
project:
- _id: 9B9290DE-BA93-11EA-9121-9846C619BF3A
grant_number: ' W1260-N35'
name: Vienna Graduate School on Computational Optimization
- _id: 268A44D6-B435-11E9-9278-68D0E5697425
call_identifier: H2020
grant_number: '805223'
name: Elastic Coordination for Scalable Machine Learning
publication: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
eisbn:
- '9798350301298'
eissn:
- 2575-7075
publication_status: published
publisher: IEEE
quality_controlled: '1'
related_material:
link:
- relation: software
url: https://github.com/IST-DASLab/pruned-vision-model-bias
status: public
title: 'Bias in pruned vision models: In-depth analysis and countermeasures'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2023'
...
---
_id: '12299'
abstract:
- lang: eng
text: 'Transfer learning is a classic paradigm by which models pretrained on large
“upstream” datasets are adapted to yield good results on “downstream” specialized
datasets. Generally, more accurate models on the “upstream” dataset tend to provide
better transfer accuracy “downstream”. In this work, we perform an in-depth investigation
of this phenomenon in the context of convolutional neural networks (CNNs) trained
on the ImageNet dataset, which have been pruned-that is, compressed by sparsifiying
their connections. We consider transfer using unstructured pruned models obtained
by applying several state-of-the-art pruning methods, including magnitude-based,
second-order, regrowth, lottery-ticket, and regularization approaches, in the
context of twelve standard transfer tasks. In a nutshell, our study shows that
sparse models can match or even outperform the transfer performance of dense models,
even at high sparsities, and, while doing so, can lead to significant inference
and even training speedups. At the same time, we observe and analyze significant
differences in the behaviour of different pruning methods. The code is available
at: https://github.com/IST-DASLab/sparse-imagenet-transfer.'
acknowledgement: he authors would like to sincerely thank Christoph Lampert and Nir
Shavit for fruitful discussions during the development of this work, and Eldar Kurtic
for experimental support. EI was supported in part by the FWF DK VGSCO, grant agreement
number W1260-N35, while AP and DA acknowledge generous support by the ERC, via Starting
Grant 805223 ScaleML.
article_processing_charge: No
arxiv: 1
author:
- first_name: Eugenia B
full_name: Iofinova, Eugenia B
id: f9a17499-f6e0-11ea-865d-fdf9a3f77117
last_name: Iofinova
orcid: 0000-0002-7778-3221
- first_name: Elena-Alexandra
full_name: Peste, Elena-Alexandra
id: 32D78294-F248-11E8-B48F-1D18A9856A87
last_name: Peste
- first_name: Mark
full_name: Kurtz, Mark
last_name: Kurtz
- first_name: Dan-Adrian
full_name: Alistarh, Dan-Adrian
id: 4A899BFC-F248-11E8-B48F-1D18A9856A87
last_name: Alistarh
orcid: 0000-0003-3650-940X
citation:
ama: 'Iofinova EB, Peste E-A, Kurtz M, Alistarh D-A. How well do sparse ImageNet
models transfer? In: 2022 IEEE/CVF Conference on Computer Vision and Pattern
Recognition. Institute of Electrical and Electronics Engineers; 2022:12256-12266.
doi:10.1109/cvpr52688.2022.01195'
apa: 'Iofinova, E. B., Peste, E.-A., Kurtz, M., & Alistarh, D.-A. (2022). How
well do sparse ImageNet models transfer? In 2022 IEEE/CVF Conference on Computer
Vision and Pattern Recognition (pp. 12256–12266). New Orleans, LA, United
States: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/cvpr52688.2022.01195'
chicago: Iofinova, Eugenia B, Elena-Alexandra Peste, Mark Kurtz, and Dan-Adrian
Alistarh. “How Well Do Sparse ImageNet Models Transfer?” In 2022 IEEE/CVF Conference
on Computer Vision and Pattern Recognition, 12256–66. Institute of Electrical
and Electronics Engineers, 2022. https://doi.org/10.1109/cvpr52688.2022.01195.
ieee: E. B. Iofinova, E.-A. Peste, M. Kurtz, and D.-A. Alistarh, “How well do sparse
ImageNet models transfer?,” in 2022 IEEE/CVF Conference on Computer Vision
and Pattern Recognition, New Orleans, LA, United States, 2022, pp. 12256–12266.
ista: 'Iofinova EB, Peste E-A, Kurtz M, Alistarh D-A. 2022. How well do sparse ImageNet
models transfer? 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.
CVPR: Computer Vision and Pattern Recognition, 12256–12266.'
mla: Iofinova, Eugenia B., et al. “How Well Do Sparse ImageNet Models Transfer?”
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Institute
of Electrical and Electronics Engineers, 2022, pp. 12256–66, doi:10.1109/cvpr52688.2022.01195.
short: E.B. Iofinova, E.-A. Peste, M. Kurtz, D.-A. Alistarh, in:, 2022 IEEE/CVF
Conference on Computer Vision and Pattern Recognition, Institute of Electrical
and Electronics Engineers, 2022, pp. 12256–12266.
conference:
end_date: 2022-06-24
location: New Orleans, LA, United States
name: 'CVPR: Computer Vision and Pattern Recognition'
start_date: 2022-06-18
date_created: 2023-01-16T10:06:00Z
date_published: 2022-09-27T00:00:00Z
date_updated: 2023-08-04T10:33:28Z
day: '27'
department:
- _id: DaAl
- _id: ChLa
doi: 10.1109/cvpr52688.2022.01195
ec_funded: 1
external_id:
arxiv:
- '2111.13445'
isi:
- '000870759105034'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2111.13445
month: '09'
oa: 1
oa_version: Preprint
page: 12256-12266
project:
- _id: 9B9290DE-BA93-11EA-9121-9846C619BF3A
grant_number: ' W1260-N35'
name: Vienna Graduate School on Computational Optimization
- _id: 268A44D6-B435-11E9-9278-68D0E5697425
call_identifier: H2020
grant_number: '805223'
name: Elastic Coordination for Scalable Machine Learning
publication: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
eissn:
- 2575-7075
publication_status: published
publisher: Institute of Electrical and Electronics Engineers
quality_controlled: '1'
related_material:
record:
- id: '13074'
relation: dissertation_contains
status: public
scopus_import: '1'
status: public
title: How well do sparse ImageNet models transfer?
type: conference
user_id: 4359f0d1-fa6c-11eb-b949-802e58b17ae8
year: '2022'
...
---
_id: '12495'
abstract:
- lang: eng
text: "Fairness-aware learning aims at constructing classifiers that not only make
accurate predictions, but also do not discriminate against specific groups. It
is a fast-growing area of\r\nmachine learning with far-reaching societal impact.
However, existing fair learning methods\r\nare vulnerable to accidental or malicious
artifacts in the training data, which can cause\r\nthem to unknowingly produce
unfair classifiers. In this work we address the problem of\r\nfair learning from
unreliable training data in the robust multisource setting, where the\r\navailable
training data comes from multiple sources, a fraction of which might not be representative
of the true data distribution. We introduce FLEA, a filtering-based algorithm\r\nthat
identifies and suppresses those data sources that would have a negative impact
on\r\nfairness or accuracy if they were used for training. As such, FLEA is not
a replacement of\r\nprior fairness-aware learning methods but rather an augmentation
that makes any of them\r\nrobust against unreliable training data. We show the
effectiveness of our approach by a\r\ndiverse range of experiments on multiple
datasets. Additionally, we prove formally that\r\n–given enough data– FLEA protects
the learner against corruptions as long as the fraction of\r\naffected data sources
is less than half. Our source code and documentation are available at\r\nhttps://github.com/ISTAustria-CVML/FLEA."
acknowledged_ssus:
- _id: ScienComp
acknowledgement: 'The authors would like to thank Bernd Prach, Elias Frantar, Alexandra
Peste, Mahdi Nikdan, and Peter Súkeník for their helpful feedback. This research
was supported by the Scientific Service Units (SSU) of IST Austria through resources
provided by Scientific Computing (SciComp). This publication was made possible by
an ETH AI Center postdoctoral fellowship granted to Nikola Konstantinov. Eugenia
Iofinova was supported in part by the FWF DK VGSCO, grant agreement number W1260-N35. '
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: Eugenia B
full_name: Iofinova, Eugenia B
id: f9a17499-f6e0-11ea-865d-fdf9a3f77117
last_name: Iofinova
orcid: 0000-0002-7778-3221
- first_name: Nikola H
full_name: Konstantinov, Nikola H
id: 4B9D76E4-F248-11E8-B48F-1D18A9856A87
last_name: Konstantinov
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Iofinova EB, Konstantinov NH, Lampert C. FLEA: Provably robust fair multisource
learning from unreliable training data. Transactions on Machine Learning Research.
2022.'
apa: 'Iofinova, E. B., Konstantinov, N. H., & Lampert, C. (2022). FLEA: Provably
robust fair multisource learning from unreliable training data. Transactions
on Machine Learning Research. ML Research Press.'
chicago: 'Iofinova, Eugenia B, Nikola H Konstantinov, and Christoph Lampert. “FLEA:
Provably Robust Fair Multisource Learning from Unreliable Training Data.” Transactions
on Machine Learning Research. ML Research Press, 2022.'
ieee: 'E. B. Iofinova, N. H. Konstantinov, and C. Lampert, “FLEA: Provably robust
fair multisource learning from unreliable training data,” Transactions on Machine
Learning Research. ML Research Press, 2022.'
ista: 'Iofinova EB, Konstantinov NH, Lampert C. 2022. FLEA: Provably robust fair
multisource learning from unreliable training data. Transactions on Machine Learning
Research.'
mla: 'Iofinova, Eugenia B., et al. “FLEA: Provably Robust Fair Multisource Learning
from Unreliable Training Data.” Transactions on Machine Learning Research,
ML Research Press, 2022.'
short: E.B. Iofinova, N.H. Konstantinov, C. Lampert, Transactions on Machine Learning
Research (2022).
date_created: 2023-02-02T20:29:57Z
date_published: 2022-12-22T00:00:00Z
date_updated: 2023-02-23T10:30:54Z
day: '22'
ddc:
- '000'
department:
- _id: ChLa
external_id:
arxiv:
- '2106.11732'
file:
- access_level: open_access
checksum: 97c8a8470759cab597abb973ca137a3b
content_type: application/pdf
creator: dernst
date_created: 2023-02-23T10:30:04Z
date_updated: 2023-02-23T10:30:04Z
file_id: '12673'
file_name: 2022_TMLR_Iofinova.pdf
file_size: 1948063
relation: main_file
success: 1
file_date_updated: 2023-02-23T10:30:04Z
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://openreview.net/forum?id=XsPopigZXV
month: '12'
oa: 1
oa_version: Published Version
project:
- _id: 9B9290DE-BA93-11EA-9121-9846C619BF3A
grant_number: ' W1260-N35'
name: Vienna Graduate School on Computational Optimization
publication: Transactions on Machine Learning Research
publication_identifier:
issn:
- 2835-8856
publication_status: published
publisher: ML Research Press
quality_controlled: '1'
related_material:
link:
- description: source code
relation: software
url: https://github.com/ISTAustria-CVML/FLEA
status: public
title: 'FLEA: Provably robust fair multisource learning from unreliable training data'
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2022'
...
---
_id: '11458'
abstract:
- lang: eng
text: 'The increasing computational requirements of deep neural networks (DNNs)
have led to significant interest in obtaining DNN models that are sparse, yet
accurate. Recent work has investigated the even harder case of sparse training,
where the DNN weights are, for as much as possible, already sparse to reduce computational
costs during training. Existing sparse training methods are often empirical and
can have lower accuracy relative to the dense baseline. In this paper, we present
a general approach called Alternating Compressed/DeCompressed (AC/DC) training
of DNNs, demonstrate convergence for a variant of the algorithm, and show that
AC/DC outperforms existing sparse training methods in accuracy at similar computational
budgets; at high sparsity levels, AC/DC even outperforms existing methods that
rely on accurate pre-trained dense models. An important property of AC/DC is that
it allows co-training of dense and sparse models, yielding accurate sparse–dense
model pairs at the end of the training process. This is useful in practice, where
compressed variants may be desirable for deployment in resource-constrained settings
without re-doing the entire training flow, and also provides us with insights
into the accuracy gap between dense and compressed models. The code is available
at: https://github.com/IST-DASLab/ACDC.'
acknowledged_ssus:
- _id: ScienComp
acknowledgement: This project has received funding from the European Research Council
(ERC) under the European Union’s Horizon 2020 research and innovation programme
(grant agreement No 805223 ScaleML), and a CNRS PEPS grant. This research was supported
by the Scientific Service Units (SSU) of IST Austria through resources provided
by Scientific Computing (SciComp). We would also like to thank Christoph Lampert
for his feedback on an earlier version of this work, as well as for providing hardware
for the Transformer-XL experiments.
article_processing_charge: No
arxiv: 1
author:
- first_name: Elena-Alexandra
full_name: Peste, Elena-Alexandra
id: 32D78294-F248-11E8-B48F-1D18A9856A87
last_name: Peste
- first_name: Eugenia B
full_name: Iofinova, Eugenia B
id: f9a17499-f6e0-11ea-865d-fdf9a3f77117
last_name: Iofinova
orcid: 0000-0002-7778-3221
- first_name: Adrian
full_name: Vladu, Adrian
last_name: Vladu
- first_name: Dan-Adrian
full_name: Alistarh, Dan-Adrian
id: 4A899BFC-F248-11E8-B48F-1D18A9856A87
last_name: Alistarh
orcid: 0000-0003-3650-940X
citation:
ama: 'Peste E-A, Iofinova EB, Vladu A, Alistarh D-A. AC/DC: Alternating Compressed/DeCompressed
training of deep neural networks. In: 35th Conference on Neural Information
Processing Systems. Vol 34. Curran Associates; 2021:8557-8570.'
apa: 'Peste, E.-A., Iofinova, E. B., Vladu, A., & Alistarh, D.-A. (2021). AC/DC:
Alternating Compressed/DeCompressed training of deep neural networks. In 35th
Conference on Neural Information Processing Systems (Vol. 34, pp. 8557–8570).
Virtual, Online: Curran Associates.'
chicago: 'Peste, Elena-Alexandra, Eugenia B Iofinova, Adrian Vladu, and Dan-Adrian
Alistarh. “AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural
Networks.” In 35th Conference on Neural Information Processing Systems,
34:8557–70. Curran Associates, 2021.'
ieee: 'E.-A. Peste, E. B. Iofinova, A. Vladu, and D.-A. Alistarh, “AC/DC: Alternating
Compressed/DeCompressed training of deep neural networks,” in 35th Conference
on Neural Information Processing Systems, Virtual, Online, 2021, vol. 34,
pp. 8557–8570.'
ista: 'Peste E-A, Iofinova EB, Vladu A, Alistarh D-A. 2021. AC/DC: Alternating Compressed/DeCompressed
training of deep neural networks. 35th Conference on Neural Information Processing
Systems. NeurIPS: Neural Information Processing Systems vol. 34, 8557–8570.'
mla: 'Peste, Elena-Alexandra, et al. “AC/DC: Alternating Compressed/DeCompressed
Training of Deep Neural Networks.” 35th Conference on Neural Information Processing
Systems, vol. 34, Curran Associates, 2021, pp. 8557–70.'
short: E.-A. Peste, E.B. Iofinova, A. Vladu, D.-A. Alistarh, in:, 35th Conference
on Neural Information Processing Systems, Curran Associates, 2021, pp. 8557–8570.
conference:
end_date: 2021-12-14
location: Virtual, Online
name: 'NeurIPS: Neural Information Processing Systems'
start_date: 2021-12-06
date_created: 2022-06-20T12:11:53Z
date_published: 2021-12-06T00:00:00Z
date_updated: 2023-06-01T12:54:45Z
day: '6'
department:
- _id: GradSch
- _id: DaAl
ec_funded: 1
external_id:
arxiv:
- '2106.12379'
intvolume: ' 34'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://proceedings.neurips.cc/paper/2021/file/48000647b315f6f00f913caa757a70b3-Paper.pdf
month: '12'
oa: 1
oa_version: Published Version
page: 8557-8570
project:
- _id: 268A44D6-B435-11E9-9278-68D0E5697425
call_identifier: H2020
grant_number: '805223'
name: Elastic Coordination for Scalable Machine Learning
publication: 35th Conference on Neural Information Processing Systems
publication_identifier:
isbn:
- '9781713845393'
issn:
- 1049-5258
publication_status: published
publisher: Curran Associates
quality_controlled: '1'
related_material:
record:
- id: '13074'
relation: dissertation_contains
status: public
scopus_import: '1'
status: public
title: 'AC/DC: Alternating Compressed/DeCompressed training of deep neural networks'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 34
year: '2021'
...