Learning & Adaptation

Research is funded by the DARPA ITMANET project, Motorola, as well as the National Science Foundation. See also the Information Theory page.

Control Variates as Screening Functions. Sofia Kyriazopoulou-Panagiotopoulou, Ioannis Kontoyiannis, and Sean Meyn. To appear in VALUETOOLS 2008 - Third International Conference on Performance Evaluation Methodologies and Tools. October 20-24, 2008, Athens, Greece.

Oja's Algorithm for Graph Clustering and Markov Spectral Decomposition. Vivek Borkar and Sean Meyn. To appear in VALUETOOLS 2008 - Third International Conference on Performance Evaluation Methodologies and Tools. October 20-24, 2008, Athens, Greece

Shannon meets Bellman: Feature based Markovian models for detection and optimization. George Mathew and Sean Meyn. To appear, 47th IEEE Conference on Decision and Control. December 9 - 11, 2008, Cancun, Mexico.

Waveform Relaxation and Graph Decomposition. George Mathew, Sean Meyn, Andrzej Banaszuk.
18th International symposium on Mathematical Theory of Networks and Systems (MTNS2008) Virginia Tech, Blacksburg, Virginia, USA July 28-August 1, 2008.

I. Kontoyiannis , L. A. Lastras-Montaño , S. P. Meyn, Exponential bounds and stopping rules for MCMC and general Markov chains. Proceedings of the 1st international conference on Performance evaluation methodolgies and tools, October 11-13, 2006, Pisa, Italy.

G. Fort, S. Meyn, E. Moulines, and P. Priouret, The ODE methods for Markov chain stability with applications to MCMC (more information)

I. Kontoyiannis and S.P. Meyn, Computable Exponential Bounds for Screened Estimation and Simulation. (more information)

E. Abbe, M. Medard, S. P. Meyn, and L. Zheng, Finding the Best Mismatched Detector for Channel Coding and Hypothesis Testing. (more information)

C. Pandit, and S.P. Meyn, Worst-Case Large-Deviations Asymptotics with Application to Queueing and Information Theory. Stochastic Processes and Applications 116(5) pp. 724-756, 2006.

C. Pandit, J. Huang, S. Meyn, V. Veeravalli, Extremal Distributions in Information Theory and Hypothesis Testing. Proceedings of the IEEE Information Theory Workshop, San Antonio, Texas, October 24-29, 2004.

V. Tadic, S.P. Meyn and R. Tempo, Randomized Algorithms for Semi-Infinite Programming Problems. Probabilistic and Randomized Methods for Design under Uncertainty, Springer Verlag, 2005.

V. Tadic and S.P. Meyn, Asymptotic Properties of Two Time-Scale Stochastic Approximation Algorithms with Constant Step Sizes, Proceedings of the 2003 American Control Conference June 4 to 6, 2003.

J. Huang, Kontoyiannis, I. and S.P. Meyn, The O.D.E. Method and Spectral Theory of Markov Operators (also available in pdf format), Proceedings of the Second Kansas Workshop on Stochastic Theory - Adaptive Control, 2001

V. Borkar and S.P. Meyn, The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning , SIAM J. Control, Vol. 38, no.2, 2000, pp. 447-69.

S.R. Rayadurgam and S.P. Meyn, Bounds on Achievable Performance in Adaptive Control, IEEE Transactions on Automatic Control, Vol 44, No 4, pp. 670--682, 1999.

L.J. Brown, S.P. Meyn, and R. Weber, Adaptive Dead-Time Compensation with Applications, IEEE J. Control Systems Technology, vol 6, pp. 335-349, 1998.

S.P. Meyn and L. J. Brown, Model Reference Adaptive Control of Time Varying and Stochastic Systems, IEEE Transactions on Automatic Control, Vol. 38, pp. 1738--1753, 1993