Sorry, you need to enable JavaScript to visit this website.

Distributed and Cooperative Learning (MLR-DIST)

TRAINING SAMPLE SELECTION FOR DEEP LEARNING OF DISTRIBUTED DATA


The success of deep learning—in the form of multi-layer neural networks — depends critically on the volume and variety of training data. Its potential is greatly compromised when training data originate in a geographically distributed manner and are subject to bandwidth constraints. This paper presents a data sampling approach to deep learning, by carefully discriminating locally available training samples based on their relative importance.

Paper Details

Authors:
Zheng Jiang, Xiaoqing Zhu, Wai-tian Tan, and Rob Liston
Submitted On:
15 September 2017 - 3:49pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster presentation for Paper #2847

(10 downloads)

Keywords

Subscribe

[1] Zheng Jiang, Xiaoqing Zhu, Wai-tian Tan, and Rob Liston, "TRAINING SAMPLE SELECTION FOR DEEP LEARNING OF DISTRIBUTED DATA", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2159. Accessed: Sep. 25, 2017.
@article{2159-17,
url = {http://sigport.org/2159},
author = {Zheng Jiang; Xiaoqing Zhu; Wai-tian Tan; and Rob Liston },
publisher = {IEEE SigPort},
title = {TRAINING SAMPLE SELECTION FOR DEEP LEARNING OF DISTRIBUTED DATA},
year = {2017} }
TY - EJOUR
T1 - TRAINING SAMPLE SELECTION FOR DEEP LEARNING OF DISTRIBUTED DATA
AU - Zheng Jiang; Xiaoqing Zhu; Wai-tian Tan; and Rob Liston
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2159
ER -
Zheng Jiang, Xiaoqing Zhu, Wai-tian Tan, and Rob Liston. (2017). TRAINING SAMPLE SELECTION FOR DEEP LEARNING OF DISTRIBUTED DATA. IEEE SigPort. http://sigport.org/2159
Zheng Jiang, Xiaoqing Zhu, Wai-tian Tan, and Rob Liston, 2017. TRAINING SAMPLE SELECTION FOR DEEP LEARNING OF DISTRIBUTED DATA. Available at: http://sigport.org/2159.
Zheng Jiang, Xiaoqing Zhu, Wai-tian Tan, and Rob Liston. (2017). "TRAINING SAMPLE SELECTION FOR DEEP LEARNING OF DISTRIBUTED DATA." Web.
1. Zheng Jiang, Xiaoqing Zhu, Wai-tian Tan, and Rob Liston. TRAINING SAMPLE SELECTION FOR DEEP LEARNING OF DISTRIBUTED DATA [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2159

A Projection-free Decentralized Algorithm for Non-convex Optimization


This paper considers a decentralized projection free algorithm for non-convex optimization in high dimension. More specifically, we propose a Decentralized Frank-Wolfe (DeFW)
algorithm which is suitable when high dimensional optimization constraints are difficult to handle by conventional projection/proximal-based gradient descent methods. We present conditions under which the DeFW algorithm converges to a stationary point and prove that the rate of convergence is as fast as ${\cal O}( 1/\sqrt{T} )$, where

Paper Details

Authors:
Anna Scaglione, Jean Lafond, Eric Moulines
Submitted On:
7 December 2016 - 11:58pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ncvx_globalsip16.pdf

(135 downloads)

Keywords

Subscribe

[1] Anna Scaglione, Jean Lafond, Eric Moulines, "A Projection-free Decentralized Algorithm for Non-convex Optimization", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1381. Accessed: Sep. 25, 2017.
@article{1381-16,
url = {http://sigport.org/1381},
author = {Anna Scaglione; Jean Lafond; Eric Moulines },
publisher = {IEEE SigPort},
title = {A Projection-free Decentralized Algorithm for Non-convex Optimization},
year = {2016} }
TY - EJOUR
T1 - A Projection-free Decentralized Algorithm for Non-convex Optimization
AU - Anna Scaglione; Jean Lafond; Eric Moulines
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1381
ER -
Anna Scaglione, Jean Lafond, Eric Moulines. (2016). A Projection-free Decentralized Algorithm for Non-convex Optimization. IEEE SigPort. http://sigport.org/1381
Anna Scaglione, Jean Lafond, Eric Moulines, 2016. A Projection-free Decentralized Algorithm for Non-convex Optimization. Available at: http://sigport.org/1381.
Anna Scaglione, Jean Lafond, Eric Moulines. (2016). "A Projection-free Decentralized Algorithm for Non-convex Optimization." Web.
1. Anna Scaglione, Jean Lafond, Eric Moulines. A Projection-free Decentralized Algorithm for Non-convex Optimization [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1381

Distributed Sequence Prediction: A consensus+innovations approach


This paper focuses on the problem of distributed sequence
prediction in a network of sparsely interconnected agents,
where agents collaborate to achieve provably reasonable
predictive performance. An expert assisted online learning
algorithm in a distributed setup of the consensus+innovations
form is proposed, in which the agents update their weights
for the experts’ predictions by simultaneously processing the
latest network losses (innovations) and the cumulative losses
obtained from neighboring agents (consensus). This paper

Paper Details

Authors:
Anit Kumar Sahu, Soummya Kar
Submitted On:
6 December 2016 - 3:37am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

GlobalSIP_talk.pdf

(114 downloads)

Keywords

Subscribe

[1] Anit Kumar Sahu, Soummya Kar, "Distributed Sequence Prediction: A consensus+innovations approach", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1357. Accessed: Sep. 25, 2017.
@article{1357-16,
url = {http://sigport.org/1357},
author = {Anit Kumar Sahu; Soummya Kar },
publisher = {IEEE SigPort},
title = {Distributed Sequence Prediction: A consensus+innovations approach},
year = {2016} }
TY - EJOUR
T1 - Distributed Sequence Prediction: A consensus+innovations approach
AU - Anit Kumar Sahu; Soummya Kar
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1357
ER -
Anit Kumar Sahu, Soummya Kar. (2016). Distributed Sequence Prediction: A consensus+innovations approach. IEEE SigPort. http://sigport.org/1357
Anit Kumar Sahu, Soummya Kar, 2016. Distributed Sequence Prediction: A consensus+innovations approach. Available at: http://sigport.org/1357.
Anit Kumar Sahu, Soummya Kar. (2016). "Distributed Sequence Prediction: A consensus+innovations approach." Web.
1. Anit Kumar Sahu, Soummya Kar. Distributed Sequence Prediction: A consensus+innovations approach [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1357

Opportunistic Spectrum Access with Temporal-Spatial Reuse in Cognitive Radio Networks


We formulate and study a multi-user multi-armed bandit (MAB) problem that exploits the temporal-spatial reuse of primary user (PU) channels so that secondary users (SUs) who do not interfere with each other can make use of the same PU channel. We first propose a centralized channel allocation policy that has logarithmic regret, but requires a central processor to solve a NP-complete optimization problem at exponentially increasing time intervals.

Paper Details

Authors:
Yi Zhang, Wee Peng Tay, Kwok Hung Li, Moez Esseghir, Dominique Gaiti
Submitted On:
15 March 2016 - 10:27am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

Poster_ICASSP2016_ZY_v1.pptx

(214 downloads)

Keywords

Subscribe

[1] Yi Zhang, Wee Peng Tay, Kwok Hung Li, Moez Esseghir, Dominique Gaiti, "Opportunistic Spectrum Access with Temporal-Spatial Reuse in Cognitive Radio Networks", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/689. Accessed: Sep. 25, 2017.
@article{689-16,
url = {http://sigport.org/689},
author = {Yi Zhang; Wee Peng Tay; Kwok Hung Li; Moez Esseghir; Dominique Gaiti },
publisher = {IEEE SigPort},
title = {Opportunistic Spectrum Access with Temporal-Spatial Reuse in Cognitive Radio Networks},
year = {2016} }
TY - EJOUR
T1 - Opportunistic Spectrum Access with Temporal-Spatial Reuse in Cognitive Radio Networks
AU - Yi Zhang; Wee Peng Tay; Kwok Hung Li; Moez Esseghir; Dominique Gaiti
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/689
ER -
Yi Zhang, Wee Peng Tay, Kwok Hung Li, Moez Esseghir, Dominique Gaiti. (2016). Opportunistic Spectrum Access with Temporal-Spatial Reuse in Cognitive Radio Networks. IEEE SigPort. http://sigport.org/689
Yi Zhang, Wee Peng Tay, Kwok Hung Li, Moez Esseghir, Dominique Gaiti, 2016. Opportunistic Spectrum Access with Temporal-Spatial Reuse in Cognitive Radio Networks. Available at: http://sigport.org/689.
Yi Zhang, Wee Peng Tay, Kwok Hung Li, Moez Esseghir, Dominique Gaiti. (2016). "Opportunistic Spectrum Access with Temporal-Spatial Reuse in Cognitive Radio Networks." Web.
1. Yi Zhang, Wee Peng Tay, Kwok Hung Li, Moez Esseghir, Dominique Gaiti. Opportunistic Spectrum Access with Temporal-Spatial Reuse in Cognitive Radio Networks [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/689

Distributed Linear Blind Source Separation over Wireless Sensor Networks with Arbitrary Connectivity Patterns


Broad areal coverage and low cost make wireless sensor networks natural platforms for blind source separation (BSS). In this context, distributed processing is attractive because of low power requirements and scalability. However, existing distributed BSS algorithms either require a fully connected pattern of connectivity or require a high computational load at each sensor node. We introduce a distributed robust BSS algorithm that uses a fully shared computation and can be applied over any connected graph.

Paper Details

Authors:
W. Bastiaan Kleijn
Submitted On:
11 March 2016 - 10:05pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

Seyed Reza Mir Alavi.pdf

(186 downloads)

Keywords

Additional Categories

Subscribe

[1] W. Bastiaan Kleijn, "Distributed Linear Blind Source Separation over Wireless Sensor Networks with Arbitrary Connectivity Patterns", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/622. Accessed: Sep. 25, 2017.
@article{622-16,
url = {http://sigport.org/622},
author = {W. Bastiaan Kleijn },
publisher = {IEEE SigPort},
title = {Distributed Linear Blind Source Separation over Wireless Sensor Networks with Arbitrary Connectivity Patterns},
year = {2016} }
TY - EJOUR
T1 - Distributed Linear Blind Source Separation over Wireless Sensor Networks with Arbitrary Connectivity Patterns
AU - W. Bastiaan Kleijn
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/622
ER -
W. Bastiaan Kleijn. (2016). Distributed Linear Blind Source Separation over Wireless Sensor Networks with Arbitrary Connectivity Patterns. IEEE SigPort. http://sigport.org/622
W. Bastiaan Kleijn, 2016. Distributed Linear Blind Source Separation over Wireless Sensor Networks with Arbitrary Connectivity Patterns. Available at: http://sigport.org/622.
W. Bastiaan Kleijn. (2016). "Distributed Linear Blind Source Separation over Wireless Sensor Networks with Arbitrary Connectivity Patterns." Web.
1. W. Bastiaan Kleijn. Distributed Linear Blind Source Separation over Wireless Sensor Networks with Arbitrary Connectivity Patterns [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/622

DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers


DQM.pdf

PDF icon DQM.pdf (259 downloads)

Paper Details

Authors:
Wei Shi, Qing Ling, Alejandro Ribeiro
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

DQM.pdf

(259 downloads)

Keywords

Additional Categories

Subscribe

[1] Wei Shi, Qing Ling, Alejandro Ribeiro, "DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/391. Accessed: Sep. 25, 2017.
@article{391-15,
url = {http://sigport.org/391},
author = {Wei Shi; Qing Ling; Alejandro Ribeiro },
publisher = {IEEE SigPort},
title = {DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers},
year = {2015} }
TY - EJOUR
T1 - DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers
AU - Wei Shi; Qing Ling; Alejandro Ribeiro
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/391
ER -
Wei Shi, Qing Ling, Alejandro Ribeiro. (2015). DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers. IEEE SigPort. http://sigport.org/391
Wei Shi, Qing Ling, Alejandro Ribeiro, 2015. DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers. Available at: http://sigport.org/391.
Wei Shi, Qing Ling, Alejandro Ribeiro. (2015). "DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers." Web.
1. Wei Shi, Qing Ling, Alejandro Ribeiro. DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/391