Learn More
Preliminary design of a complex system often involves exploring a broad design space. This may require repeated use of computationally expensive simulations. To ease the computational burden, surrogate models are built to provide rapid approximations of more expensive models. However, the surrogate models themselves are often expensive to build because they(More)
We give an optimal dynamic programming algorithm to solve a class of finite-horizon decentralized Markov decision processes (MDPs). We consider problems with a broadcast information structure that consists of a central node that only has access to its own state but can affect several outer nodes, while each outer node has access to both its own state and(More)
Church is a Turing-complete probabilistic programming language, designed for inference. By allowing for easy description and manipulation of distributions, it allows one to describe classical Al models in compact ways, providing a language for very rich expression. However, for inference in Bayes nets, Hidden Markov Models, and topic models, the very(More)
  • Jeff Wu
  • 2010
According to 2009 ITRS roadmap, advances in process technologies, introduction of new materials, and adoption of new device architectures are expected to enable CMOS scaling to 22nm node and beyond [1]. The added process complexity will likely to lead to increased process development time and cost. Predictive TCAD modeling can be invaluable to guide(More)
To my parents and my wife Ruoyan iii ACKNOWLEDGEMENTS Foremost I would like to express my deep gratitude to my advisor, Professor C. F. Jeff Wu. His inspiration, guidance, encouragement and insight helped me through these valuable years at Georgia Tech and the University of Michigan. I am grateful to Dr. Yasuo Amemiya, my co-advisor, for his guidance,(More)
We present an exact dynamic programming solution for a finite-horizon decentralized two-player Markov decision process , where player 1 only has access to its own states, while player 2 has access to both player's states but cannot affect player 1's states. The solution is obtained by solving several centralized partially-observable Markov decision(More)