---
_id: '50066'
author:
- first_name: Feng
full_name: Dou, Feng
last_name: Dou
- first_name: Lin
full_name: Wang, Lin
id: '102868'
last_name: Wang
- first_name: Shutong
full_name: Chen, Shutong
last_name: Chen
- first_name: Fangming
full_name: Liu, Fangming
last_name: Liu
citation:
ama: 'Dou F, Wang L, Chen S, Liu F. X-Stream: A Flexible, Adaptive Video Transformer
for Privacy-Preserving Video Stream Analytics. In: Proceedings of the IEEE
International Conference on Computer Communications (INFOCOM). IEEE.'
apa: 'Dou, F., Wang, L., Chen, S., & Liu, F. (n.d.). X-Stream: A Flexible, Adaptive
Video Transformer for Privacy-Preserving Video Stream Analytics. Proceedings
of the IEEE International Conference on Computer Communications (INFOCOM).
IEEE International Conference on Computer Communications (INFOCOM), Vancouver,
Canada.'
bibtex: '@inproceedings{Dou_Wang_Chen_Liu, title={X-Stream: A Flexible, Adaptive
Video Transformer for Privacy-Preserving Video Stream Analytics}, booktitle={Proceedings
of the IEEE International Conference on Computer Communications (INFOCOM)}, publisher={IEEE},
author={Dou, Feng and Wang, Lin and Chen, Shutong and Liu, Fangming} }'
chicago: 'Dou, Feng, Lin Wang, Shutong Chen, and Fangming Liu. “X-Stream: A Flexible,
Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics.” In
Proceedings of the IEEE International Conference on Computer Communications
(INFOCOM). IEEE, n.d.'
ieee: 'F. Dou, L. Wang, S. Chen, and F. Liu, “X-Stream: A Flexible, Adaptive Video
Transformer for Privacy-Preserving Video Stream Analytics,” presented at the IEEE
International Conference on Computer Communications (INFOCOM), Vancouver, Canada.'
mla: 'Dou, Feng, et al. “X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving
Video Stream Analytics.” Proceedings of the IEEE International Conference on
Computer Communications (INFOCOM), IEEE.'
short: 'F. Dou, L. Wang, S. Chen, F. Liu, in: Proceedings of the IEEE International
Conference on Computer Communications (INFOCOM), IEEE, n.d.'
conference:
end_date: 2024-05-23
location: Vancouver, Canada
name: IEEE International Conference on Computer Communications (INFOCOM)
start_date: 2024-05-20
date_created: 2023-12-22T20:24:27Z
date_updated: 2024-01-23T20:35:02Z
department:
- _id: '34'
- _id: '7'
- _id: '75'
language:
- iso: eng
publication: Proceedings of the IEEE International Conference on Computer Communications
(INFOCOM)
publication_status: accepted
publisher: IEEE
status: public
title: 'X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video
Stream Analytics'
type: conference
user_id: '102868'
year: '2024'
...
---
_id: '50065'
author:
- first_name: Marcel
full_name: Blöcher, Marcel
last_name: Blöcher
- first_name: Nils
full_name: Nedderhut, Nils
last_name: Nedderhut
- first_name: Pavel
full_name: Chuprikov, Pavel
last_name: Chuprikov
- first_name: Ramin
full_name: Khalili, Ramin
last_name: Khalili
- first_name: Patrick
full_name: Eugster, Patrick
last_name: Eugster
- first_name: Lin
full_name: Wang, Lin
id: '102868'
last_name: Wang
citation:
ama: 'Blöcher M, Nedderhut N, Chuprikov P, Khalili R, Eugster P, Wang L. Train Once
Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES.
In: Proceedings of the IEEE International Conference on Computer Communications
(INFOCOM). IEEE.'
apa: 'Blöcher, M., Nedderhut, N., Chuprikov, P., Khalili, R., Eugster, P., &
Wang, L. (n.d.). Train Once Apply Anywhere: Effective Scheduling for Network Function
Chains Running on FUMES. Proceedings of the IEEE International Conference on
Computer Communications (INFOCOM). IEEE International Conference on Computer
Communications (INFOCOM), Vancouver, Canada.'
bibtex: '@inproceedings{Blöcher_Nedderhut_Chuprikov_Khalili_Eugster_Wang, title={Train
Once Apply Anywhere: Effective Scheduling for Network Function Chains Running
on FUMES}, booktitle={Proceedings of the IEEE International Conference on Computer
Communications (INFOCOM)}, publisher={IEEE}, author={Blöcher, Marcel and Nedderhut,
Nils and Chuprikov, Pavel and Khalili, Ramin and Eugster, Patrick and Wang, Lin}
}'
chicago: 'Blöcher, Marcel, Nils Nedderhut, Pavel Chuprikov, Ramin Khalili, Patrick
Eugster, and Lin Wang. “Train Once Apply Anywhere: Effective Scheduling for Network
Function Chains Running on FUMES.” In Proceedings of the IEEE International
Conference on Computer Communications (INFOCOM). IEEE, n.d.'
ieee: 'M. Blöcher, N. Nedderhut, P. Chuprikov, R. Khalili, P. Eugster, and L. Wang,
“Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running
on FUMES,” presented at the IEEE International Conference on Computer Communications
(INFOCOM), Vancouver, Canada.'
mla: 'Blöcher, Marcel, et al. “Train Once Apply Anywhere: Effective Scheduling for
Network Function Chains Running on FUMES.” Proceedings of the IEEE International
Conference on Computer Communications (INFOCOM), IEEE.'
short: 'M. Blöcher, N. Nedderhut, P. Chuprikov, R. Khalili, P. Eugster, L. Wang,
in: Proceedings of the IEEE International Conference on Computer Communications
(INFOCOM), IEEE, n.d.'
conference:
end_date: 2024-05-23
location: Vancouver, Canada
name: IEEE International Conference on Computer Communications (INFOCOM)
start_date: 2024-05-20
date_created: 2023-12-22T20:06:42Z
date_updated: 2024-01-23T20:35:09Z
department:
- _id: '75'
language:
- iso: eng
publication: Proceedings of the IEEE International Conference on Computer Communications
(INFOCOM)
publication_status: accepted
publisher: IEEE
status: public
title: 'Train Once Apply Anywhere: Effective Scheduling for Network Function Chains
Running on FUMES'
type: conference
user_id: '102868'
year: '2024'
...
---
_id: '50807'
author:
- first_name: Haichuan
full_name: Hu, Haichuan
last_name: Hu
- first_name: Fangming
full_name: Liu, Fangming
last_name: Liu
- first_name: Qiangyu
full_name: Pei, Qiangyu
last_name: Pei
- first_name: Yongjie
full_name: Yuan, Yongjie
last_name: Yuan
- first_name: Zichen
full_name: Xu, Zichen
last_name: Xu
- first_name: Lin
full_name: Wang, Lin
id: '102868'
last_name: Wang
citation:
ama: "Hu H, Liu F, Pei Q, Yuan Y, Xu Z, Wang L. \U0001D706Grapher: A Resource-Efficient
Serverless System for GNN Serving through Graph Sharing. In: Proceedings of
the ACM Web Conference (WWW). ACM; 2024."
apa: "Hu, H., Liu, F., Pei, Q., Yuan, Y., Xu, Z., & Wang, L. (2024). \U0001D706Grapher:
A Resource-Efficient Serverless System for GNN Serving through Graph Sharing.
Proceedings of the ACM Web Conference (WWW). ACM Web Conference (WWW),
Singapore."
bibtex: "@inproceedings{Hu_Liu_Pei_Yuan_Xu_Wang_2024, title={\U0001D706Grapher:
A Resource-Efficient Serverless System for GNN Serving through Graph Sharing},
booktitle={Proceedings of the ACM Web Conference (WWW)}, publisher={ACM}, author={Hu,
Haichuan and Liu, Fangming and Pei, Qiangyu and Yuan, Yongjie and Xu, Zichen and
Wang, Lin}, year={2024} }"
chicago: "Hu, Haichuan, Fangming Liu, Qiangyu Pei, Yongjie Yuan, Zichen Xu, and
Lin Wang. “\U0001D706Grapher: A Resource-Efficient Serverless System for GNN Serving
through Graph Sharing.” In Proceedings of the ACM Web Conference (WWW).
ACM, 2024."
ieee: "H. Hu, F. Liu, Q. Pei, Y. Yuan, Z. Xu, and L. Wang, “\U0001D706Grapher: A
Resource-Efficient Serverless System for GNN Serving through Graph Sharing,” presented
at the ACM Web Conference (WWW), Singapore, 2024."
mla: "Hu, Haichuan, et al. “\U0001D706Grapher: A Resource-Efficient Serverless System
for GNN Serving through Graph Sharing.” Proceedings of the ACM Web Conference
(WWW), ACM, 2024."
short: 'H. Hu, F. Liu, Q. Pei, Y. Yuan, Z. Xu, L. Wang, in: Proceedings of the ACM
Web Conference (WWW), ACM, 2024.'
conference:
end_date: 2024-05-17
location: Singapore
name: ACM Web Conference (WWW)
start_date: 2024-05-13
date_created: 2024-01-23T20:34:27Z
date_updated: 2024-01-23T20:35:20Z
department:
- _id: '34'
- _id: '7'
- _id: '75'
language:
- iso: eng
publication: Proceedings of the ACM Web Conference (WWW)
publisher: ACM
status: public
title: "\U0001D706Grapher: A Resource-Efficient Serverless System for GNN Serving
through Graph Sharing"
type: conference
user_id: '102868'
year: '2024'
...
---
_id: '53095'
author:
- first_name: Kamran
full_name: Razavi, Kamran
last_name: Razavi
- first_name: Saeid
full_name: Ghafouri, Saeid
last_name: Ghafouri
- first_name: Max
full_name: Mühlhäuser, Max
last_name: Mühlhäuser
- first_name: Pooyan
full_name: Jamshidi, Pooyan
last_name: Jamshidi
- first_name: Lin
full_name: Wang, Lin
id: '102868'
last_name: Wang
citation:
ama: 'Razavi K, Ghafouri S, Mühlhäuser M, Jamshidi P, Wang L. Sponge: Inference
Serving with Dynamic SLOs Using In-Place Vertical Scaling. In: Proceedings
of the 4th Workshop on Machine Learning and Systems (EuroMLSys), Colocated with
EuroSys 2024. ACM; 2024.'
apa: 'Razavi, K., Ghafouri, S., Mühlhäuser, M., Jamshidi, P., & Wang, L. (2024).
Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling. Proceedings
of the 4th Workshop on Machine Learning and Systems (EuroMLSys), Colocated with
EuroSys 2024. The 4th Workshop on Machine Learning and Systems (EuroMLSys),
colocated with EuroSys 2024, Athens, Greece.'
bibtex: '@inproceedings{Razavi_Ghafouri_Mühlhäuser_Jamshidi_Wang_2024, title={Sponge:
Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling}, booktitle={Proceedings
of the 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with
EuroSys 2024}, publisher={ACM}, author={Razavi, Kamran and Ghafouri, Saeid and
Mühlhäuser, Max and Jamshidi, Pooyan and Wang, Lin}, year={2024} }'
chicago: 'Razavi, Kamran, Saeid Ghafouri, Max Mühlhäuser, Pooyan Jamshidi, and Lin
Wang. “Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling.”
In Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys),
Colocated with EuroSys 2024. ACM, 2024.'
ieee: 'K. Razavi, S. Ghafouri, M. Mühlhäuser, P. Jamshidi, and L. Wang, “Sponge:
Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling,” presented
at the The 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated
with EuroSys 2024, Athens, Greece, 2024.'
mla: 'Razavi, Kamran, et al. “Sponge: Inference Serving with Dynamic SLOs Using
In-Place Vertical Scaling.” Proceedings of the 4th Workshop on Machine Learning
and Systems (EuroMLSys), Colocated with EuroSys 2024, ACM, 2024.'
short: 'K. Razavi, S. Ghafouri, M. Mühlhäuser, P. Jamshidi, L. Wang, in: Proceedings
of the 4th Workshop on Machine Learning and Systems (EuroMLSys), Colocated with
EuroSys 2024, ACM, 2024.'
conference:
end_date: 2024-04-22
location: Athens, Greece
name: The 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with
EuroSys 2024
start_date: 2024-04-22
date_created: 2024-03-28T12:00:49Z
date_updated: 2024-03-28T12:02:23Z
department:
- _id: '34'
- _id: '7'
- _id: '75'
language:
- iso: eng
publication: Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys),
colocated with EuroSys 2024
publisher: ACM
status: public
title: 'Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling'
type: conference
user_id: '102868'
year: '2024'
...
---
_id: '29672'
author:
- first_name: Stefan Balthasar
full_name: Schneider, Stefan Balthasar
id: '35343'
last_name: Schneider
orcid: 0000-0001-8210-4011
citation:
ama: 'Schneider SB. Network and Service Coordination: Conventional and Machine
Learning Approaches".; 2022. doi:10.17619/UNIPB/1-1276 '
apa: 'Schneider, S. B. (2022). Network and Service Coordination: Conventional
and Machine Learning Approaches". https://doi.org/10.17619/UNIPB/1-1276 '
bibtex: '@book{Schneider_2022, title={Network and Service Coordination: Conventional
and Machine Learning Approaches"}, DOI={10.17619/UNIPB/1-1276 }, author={Schneider, Stefan Balthasar}, year={2022}
}'
chicago: 'Schneider, Stefan Balthasar. Network and Service Coordination: Conventional
and Machine Learning Approaches", 2022. https://doi.org/10.17619/UNIPB/1-1276 .'
ieee: 'S. B. Schneider, Network and Service Coordination: Conventional and Machine
Learning Approaches". 2022.'
mla: 'Schneider, Stefan Balthasar. Network and Service Coordination: Conventional
and Machine Learning Approaches". 2022, doi:10.17619/UNIPB/1-1276 .'
short: 'S.B. Schneider, Network and Service Coordination: Conventional and Machine
Learning Approaches", 2022.'
date_created: 2022-01-31T07:08:47Z
date_updated: 2022-02-18T08:17:36Z
department:
- _id: '75'
doi: '10.17619/UNIPB/1-1276 '
language:
- iso: eng
project:
- _id: '1'
name: 'SFB 901: SFB 901'
- _id: '4'
name: 'SFB 901 - C: SFB 901 - Project Area C'
- _id: '16'
name: 'SFB 901 - C4: SFB 901 - Subproject C4'
status: public
supervisor:
- first_name: Karl
full_name: Holger, Karl
last_name: Holger
title: 'Network and Service Coordination: Conventional and Machine Learning Approaches"'
type: dissertation
user_id: '15504'
year: '2022'
...
---
_id: '30236'
abstract:
- lang: eng
text: "Recent reinforcement learning approaches for continuous control in wireless
mobile networks have shown impressive\r\nresults. But due to the lack of open
and compatible simulators, authors typically create their own simulation environments
for training and evaluation. This is cumbersome and time-consuming for authors
and limits reproducibility and comparability, ultimately impeding progress in
the field.\r\n\r\nTo this end, we propose mobile-env, a simple and open platform
for training, evaluating, and comparing reinforcement learning and conventional
approaches for continuous control in mobile wireless networks. mobile-env is lightweight
and implements the common OpenAI Gym interface and additional wrappers, which
allows connecting virtually any single-agent or multi-agent reinforcement learning
framework to the environment. While mobile-env provides sensible default values
and can be used out of the box, it also has many configuration options and is
easy to extend. We therefore believe mobile-env to be a valuable platform for
driving meaningful progress in autonomous coordination of\r\nwireless mobile networks."
author:
- first_name: Stefan Balthasar
full_name: Schneider, Stefan Balthasar
id: '35343'
last_name: Schneider
orcid: 0000-0001-8210-4011
- first_name: Stefan
full_name: Werner, Stefan
last_name: Werner
- first_name: Ramin
full_name: Khalili, Ramin
last_name: Khalili
- first_name: Artur
full_name: Hecker, Artur
last_name: Hecker
- first_name: Holger
full_name: Karl, Holger
id: '126'
last_name: Karl
citation:
ama: 'Schneider SB, Werner S, Khalili R, Hecker A, Karl H. mobile-env: An Open Platform
for Reinforcement Learning in Wireless Mobile Networks. In: IEEE/IFIP Network
Operations and Management Symposium (NOMS). IEEE; 2022.'
apa: 'Schneider, S. B., Werner, S., Khalili, R., Hecker, A., & Karl, H. (2022).
mobile-env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks.
IEEE/IFIP Network Operations and Management Symposium (NOMS). IEEE/IFIP
Network Operations and Management Symposium (NOMS), Budapest.'
bibtex: '@inproceedings{Schneider_Werner_Khalili_Hecker_Karl_2022, title={mobile-env:
An Open Platform for Reinforcement Learning in Wireless Mobile Networks}, booktitle={IEEE/IFIP
Network Operations and Management Symposium (NOMS)}, publisher={IEEE}, author={Schneider,
Stefan Balthasar and Werner, Stefan and Khalili, Ramin and Hecker, Artur and Karl,
Holger}, year={2022} }'
chicago: 'Schneider, Stefan Balthasar, Stefan Werner, Ramin Khalili, Artur Hecker,
and Holger Karl. “Mobile-Env: An Open Platform for Reinforcement Learning in Wireless
Mobile Networks.” In IEEE/IFIP Network Operations and Management Symposium
(NOMS). IEEE, 2022.'
ieee: 'S. B. Schneider, S. Werner, R. Khalili, A. Hecker, and H. Karl, “mobile-env:
An Open Platform for Reinforcement Learning in Wireless Mobile Networks,” presented
at the IEEE/IFIP Network Operations and Management Symposium (NOMS), Budapest,
2022.'
mla: 'Schneider, Stefan Balthasar, et al. “Mobile-Env: An Open Platform for Reinforcement
Learning in Wireless Mobile Networks.” IEEE/IFIP Network Operations and Management
Symposium (NOMS), IEEE, 2022.'
short: 'S.B. Schneider, S. Werner, R. Khalili, A. Hecker, H. Karl, in: IEEE/IFIP
Network Operations and Management Symposium (NOMS), IEEE, 2022.'
conference:
end_date: 2022-04-29
location: Budapest
name: IEEE/IFIP Network Operations and Management Symposium (NOMS)
start_date: 2022-04-25
date_created: 2022-03-10T18:28:14Z
date_updated: 2022-03-10T18:28:19Z
ddc:
- '004'
department:
- _id: '75'
file:
- access_level: open_access
content_type: application/pdf
creator: stschn
date_created: 2022-03-10T18:25:41Z
date_updated: 2022-03-10T18:25:41Z
file_id: '30237'
file_name: author_version.pdf
file_size: 223412
relation: main_file
file_date_updated: 2022-03-10T18:25:41Z
has_accepted_license: '1'
keyword:
- wireless mobile networks
- network management
- continuous control
- cognitive networks
- autonomous coordination
- reinforcement learning
- gym environment
- simulation
- open source
language:
- iso: eng
oa: '1'
project:
- _id: '1'
name: 'SFB 901: SFB 901'
- _id: '4'
name: 'SFB 901 - C: SFB 901 - Project Area C'
- _id: '16'
name: 'SFB 901 - C4: SFB 901 - Subproject C4'
publication: IEEE/IFIP Network Operations and Management Symposium (NOMS)
publisher: IEEE
quality_controlled: '1'
status: public
title: 'mobile-env: An Open Platform for Reinforcement Learning in Wireless Mobile
Networks'
type: conference
user_id: '35343'
year: '2022'
...
---
_id: '32811'
abstract:
- lang: eng
text: 'The decentralized nature of multi-agent systems requires continuous data
exchange to achieve global objectives. In such scenarios, Age of Information (AoI)
has become an important metric of the freshness of exchanged data due to the error-proneness
and delays of communication systems. Communication systems usually possess dependencies:
the process describing the success or failure of communication is highly correlated
when these attempts are ``close'''' in some domain (e.g. in time, frequency, space
or code as in wireless communication) and is, in general, non-stationary. To study
AoI in such scenarios, we consider an abstract event-based AoI process $\Delta(n)$,
expressing time since the last update: If, at time $n$, a monitoring node receives
a status update from a source node (event $A(n-1)$ occurs), then $\Delta(n)$ is
reset to one; otherwise, $\Delta(n)$ grows linearly in time. This AoI process
can thus be viewed as a special random walk with resets. The event process $A(n)$
may be nonstationary and we merely assume that its temporal dependencies decay
sufficiently, described by $\alpha$-mixing. We calculate moment bounds for the
resulting AoI process as a function of the mixing rate of $A(n)$. Furthermore,
we prove that the AoI process $\Delta(n)$ is itself $\alpha$-mixing from which
we conclude a strong law of large numbers for $\Delta(n)$. These results are new,
since AoI processes have not been studied so far in this general strongly mixing
setting. This opens up future work on renewal processes with non-independent interarrival
times.'
author:
- first_name: Adrian
full_name: Redder, Adrian
id: '52265'
last_name: Redder
orcid: https://orcid.org/0000-0001-7391-4688
- first_name: Arunselvan
full_name: Ramaswamy, Arunselvan
id: '66937'
last_name: Ramaswamy
orcid: https://orcid.org/ 0000-0001-7547-8111
- first_name: Holger
full_name: Karl, Holger
id: '126'
last_name: Karl
citation:
ama: 'Redder A, Ramaswamy A, Karl H. Age of Information Process under Strongly Mixing
Communication -- Moment Bound, Mixing Rate and Strong Law. In: Proceedings
of the 58th Allerton Conference on Communication, Control, and Computing.
; 2022.'
apa: Redder, A., Ramaswamy, A., & Karl, H. (2022). Age of Information Process
under Strongly Mixing Communication -- Moment Bound, Mixing Rate and Strong Law.
Proceedings of the 58th Allerton Conference on Communication, Control, and
Computing. 58th Allerton Conference on Communication, Control, and Computing.
bibtex: '@inproceedings{Redder_Ramaswamy_Karl_2022, title={Age of Information Process
under Strongly Mixing Communication -- Moment Bound, Mixing Rate and Strong Law},
booktitle={Proceedings of the 58th Allerton Conference on Communication, Control,
and Computing}, author={Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger},
year={2022} }'
chicago: Redder, Adrian, Arunselvan Ramaswamy, and Holger Karl. “Age of Information
Process under Strongly Mixing Communication -- Moment Bound, Mixing Rate and Strong
Law.” In Proceedings of the 58th Allerton Conference on Communication, Control,
and Computing, 2022.
ieee: A. Redder, A. Ramaswamy, and H. Karl, “Age of Information Process under Strongly
Mixing Communication -- Moment Bound, Mixing Rate and Strong Law,” presented at
the 58th Allerton Conference on Communication, Control, and Computing, 2022.
mla: Redder, Adrian, et al. “Age of Information Process under Strongly Mixing Communication
-- Moment Bound, Mixing Rate and Strong Law.” Proceedings of the 58th Allerton
Conference on Communication, Control, and Computing, 2022.
short: 'A. Redder, A. Ramaswamy, H. Karl, in: Proceedings of the 58th Allerton Conference
on Communication, Control, and Computing, 2022.'
conference:
name: 58th Allerton Conference on Communication, Control, and Computing
date_created: 2022-08-15T09:59:17Z
date_updated: 2022-11-18T09:31:19Z
ddc:
- '000'
department:
- _id: '75'
has_accepted_license: '1'
language:
- iso: eng
project:
- _id: '16'
name: 'SFB 901 - C4: SFB 901 - Subproject C4'
- _id: '1'
name: 'SFB 901: SFB 901'
- _id: '4'
name: 'SFB 901 - C: SFB 901 - Project Area C'
publication: Proceedings of the 58th Allerton Conference on Communication, Control,
and Computing
status: public
title: Age of Information Process under Strongly Mixing Communication -- Moment Bound,
Mixing Rate and Strong Law
type: conference
user_id: '477'
year: '2022'
...
---
_id: '30793'
author:
- first_name: Adrian
full_name: Redder, Adrian
id: '52265'
last_name: Redder
orcid: https://orcid.org/0000-0001-7391-4688
- first_name: Arunselvan
full_name: Ramaswamy, Arunselvan
id: '66937'
last_name: Ramaswamy
orcid: https://orcid.org/ 0000-0001-7547-8111
- first_name: Holger
full_name: Karl, Holger
id: '126'
last_name: Karl
citation:
ama: 'Redder A, Ramaswamy A, Karl H. Multi-agent Policy Gradient Algorithms for
Cyber-physical Systems with Lossy Communication. In: Proceedings of the 14th
International Conference on Agents and Artificial Intelligence. SCITEPRESS
- Science and Technology Publications; 2022. doi:10.5220/0010845400003116'
apa: Redder, A., Ramaswamy, A., & Karl, H. (2022). Multi-agent Policy Gradient
Algorithms for Cyber-physical Systems with Lossy Communication. Proceedings
of the 14th International Conference on Agents and Artificial Intelligence.
https://doi.org/10.5220/0010845400003116
bibtex: '@inproceedings{Redder_Ramaswamy_Karl_2022, title={Multi-agent Policy Gradient
Algorithms for Cyber-physical Systems with Lossy Communication}, DOI={10.5220/0010845400003116},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial
Intelligence}, publisher={SCITEPRESS - Science and Technology Publications}, author={Redder,
Adrian and Ramaswamy, Arunselvan and Karl, Holger}, year={2022} }'
chicago: Redder, Adrian, Arunselvan Ramaswamy, and Holger Karl. “Multi-Agent Policy
Gradient Algorithms for Cyber-Physical Systems with Lossy Communication.” In Proceedings
of the 14th International Conference on Agents and Artificial Intelligence.
SCITEPRESS - Science and Technology Publications, 2022. https://doi.org/10.5220/0010845400003116.
ieee: 'A. Redder, A. Ramaswamy, and H. Karl, “Multi-agent Policy Gradient Algorithms
for Cyber-physical Systems with Lossy Communication,” 2022, doi: 10.5220/0010845400003116.'
mla: Redder, Adrian, et al. “Multi-Agent Policy Gradient Algorithms for Cyber-Physical
Systems with Lossy Communication.” Proceedings of the 14th International Conference
on Agents and Artificial Intelligence, SCITEPRESS - Science and Technology
Publications, 2022, doi:10.5220/0010845400003116.
short: 'A. Redder, A. Ramaswamy, H. Karl, in: Proceedings of the 14th International
Conference on Agents and Artificial Intelligence, SCITEPRESS - Science and Technology
Publications, 2022.'
date_created: 2022-04-06T07:18:36Z
date_updated: 2022-11-18T09:32:14Z
ddc:
- '006'
department:
- _id: '75'
doi: 10.5220/0010845400003116
file:
- access_level: closed
content_type: application/pdf
creator: aredder
date_created: 2022-08-31T07:10:13Z
date_updated: 2022-08-31T07:10:13Z
file_id: '33237'
file_name: ICCART2022.pdf
file_size: 298926
relation: main_file
success: 1
file_date_updated: 2022-08-31T07:10:13Z
has_accepted_license: '1'
language:
- iso: eng
project:
- _id: '16'
name: 'SFB 901 - C4: SFB 901 - Subproject C4'
- _id: '24'
name: 'NICCI-CN: Netzgewahre Regelung & regelungsgewahre Netze'
- _id: '1'
name: 'SFB 901: SFB 901'
- _id: '4'
name: 'SFB 901 - C: SFB 901 - Project Area C'
publication: Proceedings of the 14th International Conference on Agents and Artificial
Intelligence
publication_status: published
publisher: SCITEPRESS - Science and Technology Publications
status: public
title: Multi-agent Policy Gradient Algorithms for Cyber-physical Systems with Lossy
Communication
type: conference
user_id: '477'
year: '2022'
...
---
_id: '30790'
abstract:
- lang: eng
text: "Iterative distributed optimization algorithms involve multiple agents that\r\ncommunicate
with each other, over time, in order to minimize/maximize a global\r\nobjective.
In the presence of unreliable communication networks, the\r\nAge-of-Information
(AoI), which measures the freshness of data received, may be\r\nlarge and hence
hinder algorithmic convergence. In this paper, we study the\r\nconvergence of
general distributed gradient-based optimization algorithms in\r\nthe presence
of communication that neither happens periodically nor at\r\nstochastically independent
points in time. We show that convergence is\r\nguaranteed provided the random
variables associated with the AoI processes are\r\nstochastically dominated by
a random variable with finite first moment. This\r\nimproves on previous requirements
of boundedness of more than the first moment.\r\nWe then introduce stochastically
strongly connected (SSC) networks, a new\r\nstochastic form of strong connectedness
for time-varying networks. We show: If\r\nfor any $p \\ge0$ the processes that
describe the success of communication\r\nbetween agents in a SSC network are $\\alpha$-mixing
with $n^{p-1}\\alpha(n)$\r\nsummable, then the associated AoI processes are stochastically
dominated by a\r\nrandom variable with finite $p$-th moment. In combination with
our first\r\ncontribution, this implies that distributed stochastic gradient descend\r\nconverges
in the presence of AoI, if $\\alpha(n)$ is summable."
author:
- first_name: Adrian
full_name: Redder, Adrian
id: '52265'
last_name: Redder
orcid: https://orcid.org/0000-0001-7391-4688
- first_name: Arunselvan
full_name: Ramaswamy, Arunselvan
id: '66937'
last_name: Ramaswamy
orcid: https://orcid.org/ 0000-0001-7547-8111
- first_name: Holger
full_name: Karl, Holger
id: '126'
last_name: Karl
citation:
ama: Redder A, Ramaswamy A, Karl H. Distributed gradient-based optimization in the
presence of dependent aperiodic communication. arXiv:220111343. Published
online 2022.
apa: Redder, A., Ramaswamy, A., & Karl, H. (2022). Distributed gradient-based
optimization in the presence of dependent aperiodic communication. In arXiv:2201.11343.
bibtex: '@article{Redder_Ramaswamy_Karl_2022, title={Distributed gradient-based
optimization in the presence of dependent aperiodic communication}, journal={arXiv:2201.11343},
author={Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger}, year={2022}
}'
chicago: Redder, Adrian, Arunselvan Ramaswamy, and Holger Karl. “Distributed Gradient-Based
Optimization in the Presence of Dependent Aperiodic Communication.” ArXiv:2201.11343,
2022.
ieee: A. Redder, A. Ramaswamy, and H. Karl, “Distributed gradient-based optimization
in the presence of dependent aperiodic communication,” arXiv:2201.11343.
2022.
mla: Redder, Adrian, et al. “Distributed Gradient-Based Optimization in the Presence
of Dependent Aperiodic Communication.” ArXiv:2201.11343, 2022.
short: A. Redder, A. Ramaswamy, H. Karl, ArXiv:2201.11343 (2022).
date_created: 2022-04-06T06:53:38Z
date_updated: 2022-11-18T09:33:01Z
department:
- _id: '75'
external_id:
arxiv:
- '2201.11343'
language:
- iso: eng
project:
- _id: '16'
name: 'SFB 901 - C4: SFB 901 - Subproject C4'
- _id: '1'
name: 'SFB 901: SFB 901'
- _id: '4'
name: 'SFB 901 - C: SFB 901 - Project Area C'
publication: arXiv:2201.11343
status: public
title: Distributed gradient-based optimization in the presence of dependent aperiodic
communication
type: preprint
user_id: '477'
year: '2022'
...
---
_id: '30791'
abstract:
- lang: eng
text: "We present sufficient conditions that ensure convergence of the multi-agent\r\nDeep
Deterministic Policy Gradient (DDPG) algorithm. It is an example of one of\r\nthe
most popular paradigms of Deep Reinforcement Learning (DeepRL) for tackling\r\ncontinuous
action spaces: the actor-critic paradigm. In the setting considered\r\nherein,
each agent observes a part of the global state space in order to take\r\nlocal
actions, for which it receives local rewards. For every agent, DDPG\r\ntrains
a local actor (policy) and a local critic (Q-function). The analysis\r\nshows
that multi-agent DDPG using neural networks to approximate the local\r\npolicies
and critics converge to limits with the following properties: The\r\ncritic limits
minimize the average squared Bellman loss; the actor limits\r\nparameterize a
policy that maximizes the local critic's approximation of\r\n$Q_i^*$, where $i$
is the agent index. The averaging is with respect to a\r\nprobability distribution
over the global state-action space. It captures the\r\nasymptotics of all local
training processes. Finally, we extend the analysis to\r\na fully decentralized
setting where agents communicate over a wireless network\r\nprone to delays and
losses; a typical scenario in, e.g., robotic applications."
author:
- first_name: Adrian
full_name: Redder, Adrian
id: '52265'
last_name: Redder
orcid: https://orcid.org/0000-0001-7391-4688
- first_name: Arunselvan
full_name: Ramaswamy, Arunselvan
id: '66937'
last_name: Ramaswamy
orcid: https://orcid.org/ 0000-0001-7547-8111
- first_name: Holger
full_name: Karl, Holger
id: '126'
last_name: Karl
citation:
ama: Redder A, Ramaswamy A, Karl H. Asymptotic Convergence of Deep Multi-Agent Actor-Critic
Algorithms. arXiv:220100570. Published online 2022.
apa: Redder, A., Ramaswamy, A., & Karl, H. (2022). Asymptotic Convergence of
Deep Multi-Agent Actor-Critic Algorithms. In arXiv:2201.00570.
bibtex: '@article{Redder_Ramaswamy_Karl_2022, title={Asymptotic Convergence of Deep
Multi-Agent Actor-Critic Algorithms}, journal={arXiv:2201.00570}, author={Redder,
Adrian and Ramaswamy, Arunselvan and Karl, Holger}, year={2022} }'
chicago: Redder, Adrian, Arunselvan Ramaswamy, and Holger Karl. “Asymptotic Convergence
of Deep Multi-Agent Actor-Critic Algorithms.” ArXiv:2201.00570, 2022.
ieee: A. Redder, A. Ramaswamy, and H. Karl, “Asymptotic Convergence of Deep Multi-Agent
Actor-Critic Algorithms,” arXiv:2201.00570. 2022.
mla: Redder, Adrian, et al. “Asymptotic Convergence of Deep Multi-Agent Actor-Critic
Algorithms.” ArXiv:2201.00570, 2022.
short: A. Redder, A. Ramaswamy, H. Karl, ArXiv:2201.00570 (2022).
date_created: 2022-04-06T06:53:52Z
date_updated: 2022-11-18T09:33:42Z
department:
- _id: '75'
external_id:
arxiv:
- '2201.00570'
language:
- iso: eng
project:
- _id: '16'
name: 'SFB 901 - C4: SFB 901 - Subproject C4'
- _id: '1'
name: 'SFB 901: SFB 901'
- _id: '4'
name: 'SFB 901 - C: SFB 901 - Project Area C'
publication: arXiv:2201.00570
status: public
title: Asymptotic Convergence of Deep Multi-Agent Actor-Critic Algorithms
type: preprint
user_id: '477'
year: '2022'
...