uu.seUppsala University Publications
Change search
Link to record
Permanent link

Direct link
BETA
Yasini, Sholeh
Publications (6 of 6) Show all publications
Yasini, S. & Pelckmans, K. (2018). Worst-Case Prediction Performance Analysis of the Kalman Filter. IEEE Transactions on Automatic Control, 63(6), 1768-1775
Open this publication in new window or tab >>Worst-Case Prediction Performance Analysis of the Kalman Filter
2018 (English)In: IEEE Transactions on Automatic Control, ISSN 0018-9286, E-ISSN 1558-2523, Vol. 63, no 6, p. 1768-1775Article in journal (Refereed) Published
Abstract [en]

In this paper, we study the prediction performance of the Kalman filter (KF) in a worst case minimax setting as studied in online machine learning, information, and game theory. The aim is to predict the sequence of observations almost as well as the best reference predictor (comparator) sequence in a comparison class. We prove worst-case bounds on the cumulative squared prediction errors using a priori knowledge about the complexity of reference predictor sequence. In fact, the performance of the KF is derived as a function of the performance of the best reference predictor and the total amount of drift that occurs in the schedule of the best comparator.

Place, publisher, year, edition, pages
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2018
Keywords
H-infinity estimation, Kalman filter (KF), online machine learning, tracking worst-case bounds
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-357387 (URN)10.1109/TAC.2017.2757908 (DOI)000433367600018 ()
Funder
Swedish Research Council, 621-2007-6364
Available from: 2018-08-24 Created: 2018-08-24 Last updated: 2018-08-24Bibliographically approved
Yasini, S. & Pelckmans, K. (2017). High-dimensional online adaptive filtering. In: : . Paper presented at IFAC 2017, July 9–14, Toulouse, France (pp. 14106-14111).
Open this publication in new window or tab >>High-dimensional online adaptive filtering
2017 (English)Conference paper, Published paper (Refereed)
Series
IFAC-PapersOnLine, ISSN 2405-8963 ; 50:1
National Category
Signal Processing
Identifiers
urn:nbn:se:uu:diva-321311 (URN)10.1016/j.ifacol.2017.08.1851 (DOI)
Conference
IFAC 2017, July 9–14, Toulouse, France
Available from: 2017-10-18 Created: 2017-05-02 Last updated: 2018-05-17Bibliographically approved
Yasini, S., Naghibi Sistani, M. B. & Karimpour, A. (2015). Approximate Dynamic Programming for Two-player Zero-sum Game Related to H∞ Control of Unknown Nonlinear Continuous-time Systems. International Journal of Control, Automation and Systems, 13(1), 99-109
Open this publication in new window or tab >>Approximate Dynamic Programming for Two-player Zero-sum Game Related to H∞ Control of Unknown Nonlinear Continuous-time Systems
2015 (English)In: International Journal of Control, Automation and Systems, ISSN 1598-6446, E-ISSN 2005-4092, Vol. 13, no 1, p. 99-109Article in journal (Refereed) Published
Place, publisher, year, edition, pages
Springer: , 2015
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-267256 (URN)10.1007/s12555-014-0085-5 (DOI)
Available from: 2015-11-19 Created: 2015-11-19 Last updated: 2017-12-01Bibliographically approved
Yasini, S., Karimpour, A., Naghibi Sistani, M. B. & Modares, H. (2015). Online concurrent reinforcement learning algorithm to solve two-player zero-sum games for partially unknown nonlinear continuous-time systems. International journal of adaptive control and signal processing (Print), 29(4), 473-493
Open this publication in new window or tab >>Online concurrent reinforcement learning algorithm to solve two-player zero-sum games for partially unknown nonlinear continuous-time systems
2015 (English)In: International journal of adaptive control and signal processing (Print), ISSN 0890-6327, E-ISSN 1099-1115, Vol. 29, no 4, p. 473-493Article in journal (Refereed) Published
Place, publisher, year, edition, pages
Wiley: , 2015
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-267252 (URN)10.1002/acs.2485 (DOI)000353032500005 ()
Available from: 2015-11-19 Created: 2015-11-19 Last updated: 2017-12-01Bibliographically approved
Yasini, S., Karimpour, A. & Naghibi Sistani, M. B. (2014). Data-based Reinforcement Learning algorithm with Experience Replay for Solving Constrained Nonzero-sum Differential Games. In: : . Paper presented at 21st International Symposium on Mathematical Theory of Networks and Systems (MTNS 2014), Groningen, The Netherlands, July 7-11 2014. Groningen, The Netherlands
Open this publication in new window or tab >>Data-based Reinforcement Learning algorithm with Experience Replay for Solving Constrained Nonzero-sum Differential Games
2014 (English)Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Groningen, The Netherlands: , 2014
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-267270 (URN)
Conference
21st International Symposium on Mathematical Theory of Networks and Systems (MTNS 2014), Groningen, The Netherlands, July 7-11 2014
Available from: 2015-11-19 Created: 2015-11-19 Last updated: 2015-11-19
Yasini, S., Naghibi Sistani, M. B. & Karimpour, A. (2014). Policy Iteration Algorithm Based on Experience Replay to Solve H∞ Control Problem of Partially Unknown Nonlinear Systems. In: : . Paper presented at 13th European Control Conference (ECC), Strasbourg, France, June 24-27, 2014.
Open this publication in new window or tab >>Policy Iteration Algorithm Based on Experience Replay to Solve H∞ Control Problem of Partially Unknown Nonlinear Systems
2014 (English)Conference paper, Published paper (Refereed)
National Category
Control Engineering
Identifiers
urn:nbn:se:uu:diva-267278 (URN)
Conference
13th European Control Conference (ECC), Strasbourg, France, June 24-27, 2014
Available from: 2015-11-19 Created: 2015-11-19 Last updated: 2015-11-19Bibliographically approved

Search in DiVA

Show all publications