Search for: All records | NSF Public Access

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Imperceptible Attacks on Fault Detection and Diagnosis Systems in Smart Buildings

https://doi.org/10.1109/TII.2023.3288221

Alkhouri, Ismail R. ; Awad, Akram S. ; Sun, Qun Z. ; Atia, George K. ( February 2024 , IEEE Transactions on Industrial Informatics)

Free, publicly-accessible full text available February 1, 2025
Distributionally Robust Domain Adaptation

https://doi.org/10.1109/MLSP55844.2023.10286010

Awad, Akram S. ; Atia, George K. ( September 2023 , IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP))

Full Text Available
A Discriminative Approach To Unsupervised Domain Adaptation in Coarse-To-Fine Classifiers

https://doi.org/10.1109/MLSP55844.2023.10285908

Alkhouri, Ismail R. ; Awad, Akram S. ; Hatfield, Connor ; Atia, George K. ( September 2023 , IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP))

Full Text Available
Model-Free Robust Average-Reward Reinforcement Learning

Wang, Yue ; Velasquez, Alvaro ; Atia, George K ; Prater-Bennette, Ashley ; Zou, Shaofeng ( July 2023 , Proceedings of Machine Learning Research)
Krause, Andreas ; Brunskill, Emma ; Cho, Kyunghyun ; Engelhardt ; Barbara ; Sabato, Sivan ; Scarlett, Jonathan (Ed.)
Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on the robust average-reward MDPs under the modelfree setting. We first theoretically characterize the structure of solutions to the robust averagereward Bellman equation, which is essential for our later convergence analysis. We then design two model-free algorithms, robust relative value iteration (RVI) TD and robust RVI Q-learning, and theoretically prove their convergence to the optimal solution. We provide several widely used uncertainty sets as examples, including those def ined by the contamination model, total variation, Chi-squared divergence, Kullback-Leibler (KL) divergence and Wasserstein distance.
more » « less
Full Text Available
Robust Low-Tubal-Rank Tensor Completion Based on Tensor Factorization and Maximum Correntopy Criterion

https://doi.org/10.1109/TNNLS.2023.3280086

He, Yicong ; Atia, George K. ( January 2023 , IEEE Transactions on Neural Networks and Learning Systems)

Full Text Available
Patch Tracking-Based Streaming Tensor Ring Completion for Visual Data Recovery

https://doi.org/10.1109/TCSVT.2022.3190818

He, Yicong ; Atia, George K. ( December 2022 , IEEE Transactions on Circuits and Systems for Video Technology)

Full Text Available
Structured Model Selection for Recovery of Sparse Representations in Nested Periodic Dictionaries

https://doi.org/10.1109/IEEECONF56349.2022.10051897

Saidi, Pouria ; Atia, George K. ( October 2022 , Asilomar Conference on Signals, Systems, and Computers)

Full Text Available
Sketch-based community detection in evolving networks

https://doi.org/10.1103/PhysRevE.106.044306

Beckus, Andre ; Atia, George K. ( October 2022 , Physical Review E)

Full Text Available
A differentiable approach to the maximum independent set problem using dataless neural networks

https://doi.org/10.1016/j.neunet.2022.08.008

Alkhouri, Ismail R. ; Atia, George K. ; Velasquez, Alvaro ( November 2022 , Neural Networks)

Full Text Available
Coarse to Fine Two-Stage Approach to Robust Tensor Completion of Visual Data

https://doi.org/10.1109/TCYB.2022.3198932

He, Yicong ; Atia, George K. ( September 2022 , IEEE Transactions on Cybernetics)

Full Text Available

« Prev Next »