mlsanityData to 7 Oct 2026

Robust, Deep, and Reinforcement Learning for Management of Communication and Power Networks

arXiv 2202.05395 ↗First posted 8 Feb 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This thesis develops data-driven machine learning algorithms to managing and optimizing the next-generation highly complex cyberphysical systems, which desperately need ground-breaking control, monitoring, and decision making schemes that can guarantee robustness, scalability, and situational awareness. The present thesis first develops principled methods to make generic machine learning models robust against distributional uncertainties and adversarial data. Particular focus will be on parametric models where some training data are being used to learn a parametric model. The developed framework is of high interest especially when training and testing data are drawn from "slightly" different distribution. We then introduce distributionally robust learning frameworks to minimize the worst-case expected loss over a prescribed ambiguity set of training distributions quantified via Wasserstein distance. Later, we build on this robust framework to design robust semi-supervised learning over graph methods. The second part of this thesis aspires to fully unleash the potential of next-generation wired and wireless networks, where we design "smart" network entities using (deep) reinforcement learning approaches. Finally, this thesis enhances the power system operation and control. Our contribution is on sustainable distribution grids with high penetration of renewable sources and demand response programs. To account for unanticipated and rapidly changing renewable generation and load consumption scenarios, we specifically delegate reactive power compensation to both utility-owned control devices (e.g., capacitor banks), as well as smart inverters of distributed generation units with cyber-capabilities.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 235 references that are in the map. First posted on arXiv 8 Feb 2022.

Builds on

37 of 235 references.

References · 37

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  5. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  6. 2014Certifying and removing disparate impactcited by 715
  7. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  8. 2017Countering Adversarial Images using Input Transformationscited by 517
  9. 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 266
  10. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  11. 2018Adversarial Attacks and Defences: A Surveycited by 259
  12. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
25 more
  1. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  2. 2020Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studiescited by 42
  3. 2020Physics-Guided Deep Neural Networks for Power Flow Analysiscited by 32
  4. 2017Data-driven Optimal Cost Selection for Distributionally Robust Optimizationcited by 15
  5. 2019Physics-Aware Neural Networks for Distribution System State Estimationcited by 11
  6. 2015Fairness Constraints: Mechanisms for Fair Classificationcited by 10
  7. 2018Combating Adversarial Attacks Using Sparse Representationscited by 9
  8. 2018Optimal Tap Setting of Voltage Regulation Transformers Using Batch Reinforcement Learningcited by 8
  9. 2018Reinforcement Learning for Adaptive Caching with Dynamic Storage Pricingcited by 8
  10. 2019Minimum Uncertainty Based Detection of Adversaries in Deep Neural Networkscited by 8
  11. 2019Autonomous Voltage Control for Grid Operation Using Deep Reinforcement Learningcited by 8
  12. 2016Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Controlcited by 5
  13. 2019Physics-Informed Deep Neural Network Method for Limited Observability State Estimationcited by 5
  14. 2015A Transfer Learning Approach for Cache-Enabled Wireless Networkscited by 4
  15. 2020User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimizationcited by 4
  16. 2017Learning Non-Discriminatory Predictorscited by 3
  17. 2020Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Datacited by 3
  18. 2020A WLAV-based Robust Hybrid State Estimation using Circuit-theoretic Approachcited by 3
  19. 2014Optimal Geographic Caching In Cellular Networkscited by 2
  20. 2017Ultra-Dense Edge Caching under Spatio-Temporal Demand and Network Dynamicscited by 2
  21. 2018An Edge Computing Empowered Radio Access Network With UAV-Mounted FSO Fronthaul and Backhaul: Key Challenges and Approachescited by 2
  22. 2014Content-Level Selective Offloading in Heterogeneous Networks: Multi-armed Bandit Optimization and Regret Boundscited by 1
  23. 2018Decentralized Caching for Content Delivery Based on Blockchain: A Game Theoretic Perspectivecited by 1
  24. 2019A Statistical Learning Approach to Reactive Power Control in Distribution Systemscited by 1
  25. 2020Reinforcement Learning for Caching with Space-Time Popularity Dynamicscited by 1

Built on by

Not cited yet.