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

Sequential learning; sequential decision methods (MLR-SLER)

Stabilizing Multi agent Deep Reinforcement Learning by Implicitly Estimating Other Agents’ Behaviors


Deep reinforcement learning (DRL) is able to learn control policies for many complicated tasks, but it’s power has not been unleashed to handle multi-agent circumstances. Independent learning, where each agent treats others as part of the environment and learns its own policy without considering others’ policies is a simple way to apply DRL to multi-agent tasks. However, since agents’ policies change as learning proceeds, from the perspective of each agent, the environment is non-stationary, which makes conventional DRL methods inefficient.

Paper Details

Authors:
Yue Jin, Shuangqing Wei, Jian Yuan, Xudong Zhang, Chao Wang
Submitted On:
17 May 2020 - 8:31am
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

stabilizing_madrl_by_implicitly_estimating_other_agents'_behaviors.pdf

(45)

Subscribe

[1] Yue Jin, Shuangqing Wei, Jian Yuan, Xudong Zhang, Chao Wang, "Stabilizing Multi agent Deep Reinforcement Learning by Implicitly Estimating Other Agents’ Behaviors", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5384. Accessed: Oct. 24, 2020.
@article{5384-20,
url = {http://sigport.org/5384},
author = {Yue Jin; Shuangqing Wei; Jian Yuan; Xudong Zhang; Chao Wang },
publisher = {IEEE SigPort},
title = {Stabilizing Multi agent Deep Reinforcement Learning by Implicitly Estimating Other Agents’ Behaviors},
year = {2020} }
TY - EJOUR
T1 - Stabilizing Multi agent Deep Reinforcement Learning by Implicitly Estimating Other Agents’ Behaviors
AU - Yue Jin; Shuangqing Wei; Jian Yuan; Xudong Zhang; Chao Wang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5384
ER -
Yue Jin, Shuangqing Wei, Jian Yuan, Xudong Zhang, Chao Wang. (2020). Stabilizing Multi agent Deep Reinforcement Learning by Implicitly Estimating Other Agents’ Behaviors. IEEE SigPort. http://sigport.org/5384
Yue Jin, Shuangqing Wei, Jian Yuan, Xudong Zhang, Chao Wang, 2020. Stabilizing Multi agent Deep Reinforcement Learning by Implicitly Estimating Other Agents’ Behaviors. Available at: http://sigport.org/5384.
Yue Jin, Shuangqing Wei, Jian Yuan, Xudong Zhang, Chao Wang. (2020). "Stabilizing Multi agent Deep Reinforcement Learning by Implicitly Estimating Other Agents’ Behaviors." Web.
1. Yue Jin, Shuangqing Wei, Jian Yuan, Xudong Zhang, Chao Wang. Stabilizing Multi agent Deep Reinforcement Learning by Implicitly Estimating Other Agents’ Behaviors [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5384

CONTINUAL LEARNING THROUGH ONE-CLASS CLASSIFICATION USING VAE


Presentation slides of ICASSP 2020 video

Paper Details

Authors:
Andreas Brendle, Bin Yang
Submitted On:
14 May 2020 - 3:08am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

2020_04_06_ICASSP_2020_FW.pdf

(48)

Subscribe

[1] Andreas Brendle, Bin Yang, "CONTINUAL LEARNING THROUGH ONE-CLASS CLASSIFICATION USING VAE", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5242. Accessed: Oct. 24, 2020.
@article{5242-20,
url = {http://sigport.org/5242},
author = {Andreas Brendle; Bin Yang },
publisher = {IEEE SigPort},
title = {CONTINUAL LEARNING THROUGH ONE-CLASS CLASSIFICATION USING VAE},
year = {2020} }
TY - EJOUR
T1 - CONTINUAL LEARNING THROUGH ONE-CLASS CLASSIFICATION USING VAE
AU - Andreas Brendle; Bin Yang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5242
ER -
Andreas Brendle, Bin Yang. (2020). CONTINUAL LEARNING THROUGH ONE-CLASS CLASSIFICATION USING VAE. IEEE SigPort. http://sigport.org/5242
Andreas Brendle, Bin Yang, 2020. CONTINUAL LEARNING THROUGH ONE-CLASS CLASSIFICATION USING VAE. Available at: http://sigport.org/5242.
Andreas Brendle, Bin Yang. (2020). "CONTINUAL LEARNING THROUGH ONE-CLASS CLASSIFICATION USING VAE." Web.
1. Andreas Brendle, Bin Yang. CONTINUAL LEARNING THROUGH ONE-CLASS CLASSIFICATION USING VAE [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5242

SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection


Weakly supervised learning algorithms are critical for scaling audio event detection to several hundreds of sound categories. Such learning models should not only disambiguate sound events efficiently with minimal class-specific annotation but also be robust to label noise, which is more apparent with weak labels instead of strong annotations. In this work, we propose a new framework for designing learning models with weak supervision by bridging ideas from sequential learning and knowledge distillation.

Paper Details

Authors:
Anurag Kumar, Vamsi Krishna Ithapu
Submitted On:
13 May 2020 - 11:26pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

secost_icassp2020.pdf

(36)

Subscribe

[1] Anurag Kumar, Vamsi Krishna Ithapu, "SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5216. Accessed: Oct. 24, 2020.
@article{5216-20,
url = {http://sigport.org/5216},
author = {Anurag Kumar; Vamsi Krishna Ithapu },
publisher = {IEEE SigPort},
title = {SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection},
year = {2020} }
TY - EJOUR
T1 - SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection
AU - Anurag Kumar; Vamsi Krishna Ithapu
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5216
ER -
Anurag Kumar, Vamsi Krishna Ithapu. (2020). SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection. IEEE SigPort. http://sigport.org/5216
Anurag Kumar, Vamsi Krishna Ithapu, 2020. SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection. Available at: http://sigport.org/5216.
Anurag Kumar, Vamsi Krishna Ithapu. (2020). "SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection." Web.
1. Anurag Kumar, Vamsi Krishna Ithapu. SeCoST: Sequential Co-Supervision For Large Scale Weakly Labeled Audio Event Detection [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5216

Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication


For lossy image compression, we develop a neural-based system which learns a nonlinear estimator for decoding from quantized representations. The system links two recurrent networks that \help" each other reconstruct same target image patches using complementary portions of spatial context that communicate via gradient signals. This dual agent system builds upon prior work that proposed the iterative refinement algorithm for recurrent neural network (RNN)based decoding which improved image reconstruction compared to standard decoding techniques.

Paper Details

Authors:
Ankur Mali, Alexander G. Ororbia, C. Lee Giles
Submitted On:
31 March 2020 - 4:39pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Session:
Document Year:
Cite

Document Files

DCC_2020_Ankur Mali.pptx

(60)

Subscribe

[1] Ankur Mali, Alexander G. Ororbia, C. Lee Giles , "Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5086. Accessed: Oct. 24, 2020.
@article{5086-20,
url = {http://sigport.org/5086},
author = { Ankur Mali; Alexander G. Ororbia; C. Lee Giles },
publisher = {IEEE SigPort},
title = {Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication},
year = {2020} }
TY - EJOUR
T1 - Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication
AU - Ankur Mali; Alexander G. Ororbia; C. Lee Giles
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5086
ER -
Ankur Mali, Alexander G. Ororbia, C. Lee Giles . (2020). Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication. IEEE SigPort. http://sigport.org/5086
Ankur Mali, Alexander G. Ororbia, C. Lee Giles , 2020. Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication. Available at: http://sigport.org/5086.
Ankur Mali, Alexander G. Ororbia, C. Lee Giles . (2020). "Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication." Web.
1. Ankur Mali, Alexander G. Ororbia, C. Lee Giles . Sibling Neural Estimators: Improving Iterative Image Decoding with Gradient Communication [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5086

Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization)


In this paper, we derive generic bounds on the maximum deviations in prediction errors for sequential prediction via an information-theoretic approach. The fundamental bounds are shown to depend only on the conditional entropy of the data point to be predicted given the previous data points. In the asymptotic case, the bounds are achieved if and only if the prediction error is white and uniformly distributed.

Paper Details

Authors:
Song Fang, Quanyan Zhu
Submitted On:
24 October 2019 - 4:45pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

postertemplate.pdf

(122)

Subscribe

[1] Song Fang, Quanyan Zhu, "Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization)", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4890. Accessed: Oct. 24, 2020.
@article{4890-19,
url = {http://sigport.org/4890},
author = {Song Fang; Quanyan Zhu },
publisher = {IEEE SigPort},
title = {Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization)},
year = {2019} }
TY - EJOUR
T1 - Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization)
AU - Song Fang; Quanyan Zhu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4890
ER -
Song Fang, Quanyan Zhu. (2019). Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization). IEEE SigPort. http://sigport.org/4890
Song Fang, Quanyan Zhu, 2019. Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization). Available at: http://sigport.org/4890.
Song Fang, Quanyan Zhu. (2019). "Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization)." Web.
1. Song Fang, Quanyan Zhu. Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization) [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4890

Minimax Active Learning via Minimal Model Capacity


Active learning is a form of machine learning which combines supervised learning and feedback to minimize the training set size, subject to low generalization errors. Since direct optimization of the generalization error is difficult, many heuristics have been developed which lack a firm theoretical foundation. In this paper, a new information theoretic criterion is proposed based on a minimax log-loss regret formulation of the active learning problem. In the first part of this paper, a Redundancy Capacity theorem for active learning is derived along with an optimal learner.

Paper Details

Authors:
Meir Feder
Submitted On:
16 October 2019 - 4:02pm
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

MLSP_2019_Minimax_Active_Learning_via_Minimal_Model_Capacity.pdf

(143)

Subscribe

[1] Meir Feder , "Minimax Active Learning via Minimal Model Capacity", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4876. Accessed: Oct. 24, 2020.
@article{4876-19,
url = {http://sigport.org/4876},
author = {Meir Feder },
publisher = {IEEE SigPort},
title = {Minimax Active Learning via Minimal Model Capacity},
year = {2019} }
TY - EJOUR
T1 - Minimax Active Learning via Minimal Model Capacity
AU - Meir Feder
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4876
ER -
Meir Feder . (2019). Minimax Active Learning via Minimal Model Capacity. IEEE SigPort. http://sigport.org/4876
Meir Feder , 2019. Minimax Active Learning via Minimal Model Capacity. Available at: http://sigport.org/4876.
Meir Feder . (2019). "Minimax Active Learning via Minimal Model Capacity." Web.
1. Meir Feder . Minimax Active Learning via Minimal Model Capacity [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4876

ONLINE ANOMALY DETECTION IN MULTIVARIATE SETTINGS

Paper Details

Authors:
Mahsa Mozaffari, Yasin Yilmaz
Submitted On:
14 October 2019 - 5:31pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

mlsp-presentation copy.pptx

(86)

Subscribe

[1] Mahsa Mozaffari, Yasin Yilmaz, "ONLINE ANOMALY DETECTION IN MULTIVARIATE SETTINGS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4871. Accessed: Oct. 24, 2020.
@article{4871-19,
url = {http://sigport.org/4871},
author = {Mahsa Mozaffari; Yasin Yilmaz },
publisher = {IEEE SigPort},
title = {ONLINE ANOMALY DETECTION IN MULTIVARIATE SETTINGS},
year = {2019} }
TY - EJOUR
T1 - ONLINE ANOMALY DETECTION IN MULTIVARIATE SETTINGS
AU - Mahsa Mozaffari; Yasin Yilmaz
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4871
ER -
Mahsa Mozaffari, Yasin Yilmaz. (2019). ONLINE ANOMALY DETECTION IN MULTIVARIATE SETTINGS. IEEE SigPort. http://sigport.org/4871
Mahsa Mozaffari, Yasin Yilmaz, 2019. ONLINE ANOMALY DETECTION IN MULTIVARIATE SETTINGS. Available at: http://sigport.org/4871.
Mahsa Mozaffari, Yasin Yilmaz. (2019). "ONLINE ANOMALY DETECTION IN MULTIVARIATE SETTINGS." Web.
1. Mahsa Mozaffari, Yasin Yilmaz. ONLINE ANOMALY DETECTION IN MULTIVARIATE SETTINGS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4871

Variational and Hierarchical Recurrent Autoencoder


Despite a great success in learning representation for image data, it is challenging to learn the stochastic latent features from natural language based on variational inference. The difficulty in stochastic sequential learning is due to the posterior collapse caused by an autoregressive decoder which is prone to be too strong to learn sufficient latent information during optimization. To compensate this weakness in learning procedure, a sophisticated latent structure is required to assure good convergence so that random features are sufficiently captured for sequential decoding.

Paper Details

Authors:
Jen-Tzung Chien and Chun-Wei Wang
Submitted On:
7 May 2019 - 8:19pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

[ICASSP 2019] Variational and hierarchical recurrent autoencoder.pdf

(161)

Icassp19_hier.pdf

(117)

Subscribe

[1] Jen-Tzung Chien and Chun-Wei Wang, "Variational and Hierarchical Recurrent Autoencoder", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3968. Accessed: Oct. 24, 2020.
@article{3968-19,
url = {http://sigport.org/3968},
author = {Jen-Tzung Chien and Chun-Wei Wang },
publisher = {IEEE SigPort},
title = {Variational and Hierarchical Recurrent Autoencoder},
year = {2019} }
TY - EJOUR
T1 - Variational and Hierarchical Recurrent Autoencoder
AU - Jen-Tzung Chien and Chun-Wei Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3968
ER -
Jen-Tzung Chien and Chun-Wei Wang. (2019). Variational and Hierarchical Recurrent Autoencoder. IEEE SigPort. http://sigport.org/3968
Jen-Tzung Chien and Chun-Wei Wang, 2019. Variational and Hierarchical Recurrent Autoencoder. Available at: http://sigport.org/3968.
Jen-Tzung Chien and Chun-Wei Wang. (2019). "Variational and Hierarchical Recurrent Autoencoder." Web.
1. Jen-Tzung Chien and Chun-Wei Wang. Variational and Hierarchical Recurrent Autoencoder [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3968

BAYESIAN QUICKEST CHANGE POINT DETECTION WITH MULTIPLE CANDIDATES OF POST-CHANGE MODELS


We study the quickest change point detection for systems with multiple possible post-change models. A change point is the time instant at which the distribution of a random process changes. We consider the case that the post-change model is from a finite set of possible models. Under the Bayesian setting, the objective is to minimize the average detection delay (ADD), subject to upper bounds on the probability of false alarm (PFA). The proposed algorithm is a threshold-based sequential test.

Paper Details

Authors:
Samrat Nath, Jingxian Wu
Submitted On:
24 November 2018 - 2:22pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Change_Detection_GlobalSIP18.pdf

(175)

Subscribe

[1] Samrat Nath, Jingxian Wu, "BAYESIAN QUICKEST CHANGE POINT DETECTION WITH MULTIPLE CANDIDATES OF POST-CHANGE MODELS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3771. Accessed: Oct. 24, 2020.
@article{3771-18,
url = {http://sigport.org/3771},
author = {Samrat Nath; Jingxian Wu },
publisher = {IEEE SigPort},
title = {BAYESIAN QUICKEST CHANGE POINT DETECTION WITH MULTIPLE CANDIDATES OF POST-CHANGE MODELS},
year = {2018} }
TY - EJOUR
T1 - BAYESIAN QUICKEST CHANGE POINT DETECTION WITH MULTIPLE CANDIDATES OF POST-CHANGE MODELS
AU - Samrat Nath; Jingxian Wu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3771
ER -
Samrat Nath, Jingxian Wu. (2018). BAYESIAN QUICKEST CHANGE POINT DETECTION WITH MULTIPLE CANDIDATES OF POST-CHANGE MODELS. IEEE SigPort. http://sigport.org/3771
Samrat Nath, Jingxian Wu, 2018. BAYESIAN QUICKEST CHANGE POINT DETECTION WITH MULTIPLE CANDIDATES OF POST-CHANGE MODELS. Available at: http://sigport.org/3771.
Samrat Nath, Jingxian Wu. (2018). "BAYESIAN QUICKEST CHANGE POINT DETECTION WITH MULTIPLE CANDIDATES OF POST-CHANGE MODELS." Web.
1. Samrat Nath, Jingxian Wu. BAYESIAN QUICKEST CHANGE POINT DETECTION WITH MULTIPLE CANDIDATES OF POST-CHANGE MODELS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3771

Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations

Paper Details

Authors:
Fan Zhang, Qiong Wu, Hao Wang, Yuanming Shi
Submitted On:
20 June 2018 - 9:26pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations

(400)

Subscribe

[1] Fan Zhang, Qiong Wu, Hao Wang, Yuanming Shi, "Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3276. Accessed: Oct. 24, 2020.
@article{3276-18,
url = {http://sigport.org/3276},
author = {Fan Zhang; Qiong Wu; Hao Wang; Yuanming Shi },
publisher = {IEEE SigPort},
title = {Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations},
year = {2018} }
TY - EJOUR
T1 - Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations
AU - Fan Zhang; Qiong Wu; Hao Wang; Yuanming Shi
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3276
ER -
Fan Zhang, Qiong Wu, Hao Wang, Yuanming Shi. (2018). Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations. IEEE SigPort. http://sigport.org/3276
Fan Zhang, Qiong Wu, Hao Wang, Yuanming Shi, 2018. Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations. Available at: http://sigport.org/3276.
Fan Zhang, Qiong Wu, Hao Wang, Yuanming Shi. (2018). "Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations." Web.
1. Fan Zhang, Qiong Wu, Hao Wang, Yuanming Shi. Topological Interference Alignment via Generalized Low-Rank Optimization with Sequential Convex Approximations [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3276

Pages