Publications

Selected Recent Publications

  • Y. Arslantas, E. Yuceel, and M. O. Sayin. “Strategizing against Q-learners: A control-theoretical approach”, IEEE Control Systems Letters, 2024. [url]
  • M. O. Sayin, K. Zhang, and A. Ozdaglar, “Fictitious play in Markov games with single controller,” in ACM Conference on Economics and Computation (EC), 2022. [url]
  • M. O. Sayin, F. Parise, and A. Ozdaglar, “Fictitious play in zero-sum stochastic games,” SIAM Journal on Control and Optimization, 2022. [url][poster]
  • A. Ozdaglar, M. O. Sayin and K. Zhang. Independent Learning in Stochastic Games. In Proceedings of the International Congress of Mathematicians (ICM’22), vol. 7, pp. 5340-5373, 2022. [url]
  • M. O. Sayin*, K. Zhang*, D. S. Leslie, T. Başar, and A. Ozdaglar, “Decentralized Q-learning in zero-sum Markov games,” in NeurIPS, 2021. [url] [poster]

Preprints

  • Y. Arslantas, A. S. Donmez, E. Yuceel, and M. O. Sayin. Vulnerability assessment of reinforcement learning in stochastic security games, 2024.
  • Y. Arslantas and M. O. Sayin. Strategic control of experience-weighted attraction model in human-AI interactions, 2024.
  • Y. Saltan, A. Kosay, C.-W. Lin, and M. O. Sayin. Strategic control of intersections for efficient traffic routing without tolls, 2024.
  • A. S. Donmez, Y. Arslantas, and M. O. Sayin. Team collaboration vs competition: New fictitious play dynamics for multi-team zero-sum games, arXiv:2402.02147, 2024. [url]
  • Y. Arslantas, E. Yuceel, Y. Yalin, and M. O. Sayin. Convergence of heterogeneous learning dynamics in zero-sum stochastic games, arXiv:2311.00778, 2023. [url]
  • M. O. Sayin. Finite-horizon approximations and episodic equilibrium for stochastic games, arXiv:2310.07256v2, 2024. [url]
  • M. O. Sayin and O. Unlu. Logit-Q dynamics for efficient learning in stochastic teams, arXiv:2302.09806v2, 2024. [url]

Journals

  1. K. Zhang, M. O. Sayin, and A. Ozdaglar, “(Smooth) fictitious play in identical-interest stochastic games with independent continuation-payoff estimates,” Applied and Computational Mathematics, Special Issue: Control, Teams, and Games, (dedicated in honor of Tamer Başar), in print.
  2. Y. Arslantas, E. Yuceel, and M. O. Sayin, “Strategizing against Q-learners: A control-theoretical approach,” IEEE Control Systems Letters, 2024. [url]
  3. M. O. Sayin, F. Parise, and A. Ozdaglar, “Fictitious play in zero-sum stochastic games,” SIAM Journal on Control and Optimization, 2022. [url][poster]
  4. M. O. Sayin and T. Başar, “Bayesian persuasion with state-dependent quadratic cost measures,” IEEE Transactions on Automatic Control, 2022. [url]
  5. M. O. Sayin and T. Başar, “Persuasion-based robust sensor design against attackers with unknown control objectives,” IEEE Transactions on Automatic Control, 2021. [url]
  6. M. O. Sayin, C.-W. Lin, E. Kang, S. Shiraishi, and T. Başar, “Reliable smart road signs,” IEEE Transactions on Intelligent Transportation Systems, 2020. [url]
  7. M. O. Sayin, E. Akyol, and T. Başar, “Hierarchical multi-stage Gaussian signaling games in noncooperative communication and control systems,” Automatica, 2019. [url]
  8. M. O. Sayin, C.-W. Lin, S. Shiraishi, J. Shen, and T. Başar, “Information-driven autonomous intersection control via incentive compatible mechanisms,” IEEE Transactions on Intelligent Transportation Systems, 2019. [url]
  9. N. D. Vanli, M. O. Sayin, M. Mohaghegh, H. Ozkan, and S. S. Kozat, “Nonlinear regression via incremental decision trees,” Pattern Recognition, 2019. [url]
  10. O. F. Kilic, T. Ergen, M. O. Sayin, and S. S. Kozat, “Team-optimal online estimation of dynamic parameters over distributed tree networks,” Signal Processing, 2019. [url]
  11. M. O. Sayin, N. D. Vanli, S. S. Kozat, and T. Başar, “Stochastic subgradient algorithms for strongly convex optimization over distributed networks,” IEEE Transactions on Network Science and Engineering, 2017. [url][Runner-up of the 2019 IEEE TNSE Best Paper Award]
  12. M. O. Sayin, S. S. Kozat,  and T. Başar, “Team-optimal distributed MMSE estimation in general and tree networks,” Digital Signal Processing, 2017. [url]
  13. D. Kari, I. Marivani, F. Khan, M. O. Sayin, and S. S. Kozat, “Robust adaptive algorithms for underwater acoustic channel estimation and their performance analysis,” Digital Signal Processing, 2017. [url]
  14. N. D. Vanli, M. O. Sayin, I. Delibalta, and S. S. Kozat, “Sequential nonlinear learning for distributed multi-agent systems via extreme learning machines,” IEEE Transactions on Neural Networks and Learning Systems, 2017. [url]
  15. N. D. Vanli, K. Gokcesu, M. O. Sayin, H. Yildiz, and S. S. Kozat, “Sequential prediction over hierarchical structures,” IEEE Transactions on Signal Processing, 2016. [url]
  16. O. F. Kilic, M. O. Sayin, I. Delibalta, and S. S. Kozat, “Computationally highly efficient mixture of adaptive filters,” Signal, Image, and Video Processing, 2016. [url]
  17. M. O. Sayin, Y. Yilmaz, A. Demir, and S. S. Kozat, “Krylov proportionate normalized least mean fourth approach: Formulation and performance analysis,” Signal Processing, 2015. [url]
  18. M. O. Sayin and S. S. Kozat, “Compressive diffusion strategies over distributed networks for reduced communication load,” IEEE Transactions on Signal Processing, 2014. [url]
  19. M. O. Sayin, N. D. Vanli, and S. S. Kozat, “A novel family of adaptive filtering algorithms based on the logarithmic cost,” IEEE Transactions on Signal Processing, 2014. [url]
  20. M. O. Sayin and S. S. Kozat, “Single bit and reduced dimension diffusion strategies over distributed networks,” IEEE Signal Processing Letters, 2013. [url]

Chapters in Edited Volumes

  1. A. Ozdaglar, M. O. Sayin and K. Zhang. Independent Learning in Stochastic Games. In Proceedings of the International Congress of Mathematicians (ICM’22), vol. 7, pp. 5340-5373, 2022. [url]
  2. M. O. Sayin and T. Başar. Deception-As-Defense Framework for Cyber-Physical Systems. In Safety, Security, and Privacy for Cyber-Physical Systems, Springer, 2021. [url]
  3. M. O. Sayin, et al. Minimax Detection (MAD) for Computer Security: A Dynamic Program Characterization. In Game Theory and Machine Learning for Cyber Security, John Wiley & Sons, 2021. [url]

Patents

  1. M. O. Sayin, C.-W. Lin, S. Shiraishi, “Managing Roadway Intersections for Vehicles,” US Patent US11151869B2, Granted on Oct. 19, 2021. [url]

Conferences

  1. A. S. Donmez and M. O. Sayin, “Generalized individual Q-learning for polymatrix games with partial observations”, in IEEE CDC, 2024.
  2. O. Unlu and M. O. Sayin, “Episodic logit-Q dynamics for efficient learning in stochastic teams,” in IEEE CDC, 2023. [url]
  3. S.-C. Huang, K.-E. Lin, C.-Y. Kuo, L.-H. Lin, M. O. Sayin, and C.-W. Lin, “Reinforcement-learning-based job-shop scheduling for intelligent intersection management,” in Design, Automation and Test in Europe Conference (DATE), 2023. [url]
  4. M. O. Sayin, “On the global convergence of stochastic fictitious play in stochastic games with turn-based controllers”, in IEEE CDC, 2022. [url]
  5. M. O. Sayin, K. Zhang, and A. Ozdaglar, “Fictitious play in Markov games with single controller,” in ACM EC, 2022. [url]
  6. M. O. Sayin and K. A. Cetiner, “On the heterogeneity of independent learning dynamics in zero-sum stochastic games”, in L4DC, 2022. [pdf][url][poster]
  7. M. O. Sayin*, K. Zhang*, D. S. Leslie, T. Başar, and A. Ozdaglar, “Decentralized Q-learning in zero-sum Markov games,” in NeurIPS, 2021. [url] [poster]
  8. M. O. Sayin*, K. Zhang*, D. S. Leslie, T. Başar, and A. Ozdaglar, “Decentralized Q-learning in zero-sum Markov games,” in Workshop on Reinforcement Learning Theory at ICML, 2021.
  9. M. O. Sayin and T. Başar, “On the optimality of linear signaling to deceive Kalman filters over finite/infinite horizons,” in GameSec, 2019. [pdf][url]
  10. M. O. Sayin, H. Hosseini, R. Poovendran, and T. Başar, “A game theoretical framework for inter-process adversarial intervention detection,” in GameSec, 2018. [url]
  11. M. O. Sayin and T. Başar, “Dynamic information disclosure for deception,” in IEEE CDC, 2018. [pdf][url]
  12. M. O. Sayin and T. Başar, “Secure sensor design for resiliency of control systems prior to attack detection,” in IEEE CCTA, 2018. [pdf][url]
  13. M. O. Sayin and T. Başar, “Deceptive multi-dimensional information disclosure over a Gaussian channel,” in ACC, 2018. [pdf][url]
  14. M. O. Sayin, C.-W. Lin, S. Shiraishi, and T. Başar, “Reliable intersection control in non-cooperative environments,” in ACC, 2018. [url]
  15. B. Zheng, M. O. Sayin, C.-W. Lin, S. Shiraishi, and Q. Zhu, “Timing and security analysis of VANET-based intelligent transportation systems,” in IEEE ICCAD, 2017. [url]
  16. M. O. Sayin and T. Başar, “Secure sensor design for cyber-physical systems against advanced persistent threats,” in GameSec, 2017. [pdf][url]
  17. M. O. Sayin, E. Akyol, and T. Başar, “Strategic control of a tracking system,” in IEEE CDC, 2016. [pdf][url]
  18. M. O. Sayin, E. Akyol, and T. Başar, “On the structure of equilibrium strategies in dynamic Gaussian signaling games,” in IEEE MSC, 2016. [url]
  19. O. F. Kilic, M. O. Sayin, I. Delibalta, and S. S. Kozat, “Mixture of set membership filters approach for big data signal processing,” in IEEE SIU, 2016. [url] [Best Student Paper Award]
  20. M. O. Sayin, N. D. Vanli, I. Delibalta, and S. S. Kozat, “Efficient and distributed tracking of evolving state,” in IEEE MLSP, 2015. [url]
  21. N. D. Vanli, M. O. Sayin, I. Delibalta, and S. S. Kozat, “Universal online prediction via order preserving patterns,” in IEEE MLSP, 2015. [url]
  22. M. O. Sayin, N. D. Vanli, I. Delibalta, and S. S. Kozat, “Optimal and efficient distributed online learning for big data,” in IEEE Big Data Congress, 2015. [url]
  23. N. D. Vanli, M. O. Sayin, and S. S. Kozat, “Twice-universal piecewise linear regression via infinite depth context trees,” in IEEE ICASSP, 2015. [url]
  24. M. O. Sayin, N. D. Vanli, T. Goze, and S. S. Kozat, “Communication efficient channel estimation over distributed networks,” in IEEE GlobalSIP, 2014. [url]
  25. N. D. Vanli, M. O. Sayin, T. Goze, and S. S. Kozat, “Energy consumption forecasting via order preserving pattern matching,” in IEEE GlobalSIP, 2014. [url]
  26. N. D. Vanli, M. O. Sayin, S. Ergut, and S. S. Kozat, “Piecewise nonlinear regression via decision adaptive trees,” in EUSIPCO, 2014. [url]
  27. N. D. Vanli, M. O. Sayin, S. Ergut, and S. S. Kozat, “Comprehensive lower bounds on sequential prediction,” in EUSIPCO, 2014. [url]
  28. M. O. Sayin, N. D. Vanli, and S. S. Kozat, “Logarithmic regret bound over diffusion based distributed estimation,” in IEEE ICASSP, 2014. [url]
  29. M. O. Sayin, N. D. Vanli, and S. S. Kozat, “Improved convergence performance of adaptive algorithms through logarithmic cost,” in IEEE ICASSP, 2014. [url]
  30. M. O. Sayin, N. D. Vanli, and S. S. Kozat, “Robust set-membership filtering algorithms against impulsive noise,” in IEEE SIU, 2014. [url]
  31. M. O. Sayin, N. D. Vanli, and S. S. Kozat, “Performance analysis of scalar diffusion strategy over distributed networks,” in IEEE SIU, 2014. [url]
  32. N. D. Vanli, M. O. Sayin, and S. S. Kozat, “Competitive linear MMSE estimation under structured data uncertainties,” in IEEE SIU, 2014. [url]