Mohammad Rasouli

Mukul Gagrani, Yi Ouyang, Mohammad Rasouli et al.

Consider a remote estimation problem where a sensor wants to communicate the state of an uncertain source to a remote estimator over a finite time horizon. The uncertain source is modeled as an autoregressive process with bounded noise. Given that the sensor has a limited communication budget, the sensor must decide when to transmit the state to the estimator who has to produce real-time estimates of the source state. In this paper, we consider the problem of finding a scheduling strategy for the sensor and an estimation strategy for the estimator to jointly minimize the worst-case maximum instantaneous estimation error over the time horizon. This leads to a decentralized minimax decision-making problem. We obtain a complete characterization of optimal strategies for this decentralized minimax problem. In particular, we show that an open loop communication scheduling strategy is optimal and the optimal estimate depends only on the most recently received sensor observation.

Mohammad Rasouli, Ravi Chiruvolu, Ali Risheh

With the investment landscape becoming more competitive, efficiently scaling deal sourcing and improving deal insights have become a dominant strategy for funds. While funds are already spending significant efforts on these two tasks, they cannot be scaled with traditional approaches; hence, there is a surge in automating them. Many third party software providers have emerged recently to address this need with productivity solutions, but they fail due to a lack of personalization for the fund, privacy constraints, and natural limits of software use cases. Therefore, most major funds and many smaller funds have started developing their in-house AI platforms: a game changer for the industry. These platforms grow smarter by direct interactions with the fund and can be used to provide personalized use cases. Recent developments in large language models, e.g. ChatGPT, have provided an opportunity for other funds to also develop their own AI platforms. While not having an AI platform now is not a competitive disadvantage, it will be in two years. Funds require a practical plan and corresponding risk assessments for such AI platforms.

Mohammad Rasouli, Tao Sun, Ram Rajagopal

We propose Federated Generative Adversarial Network (FedGAN) for training a GAN across distributed sources of non-independent-and-identically-distributed data sources subject to communication and privacy constraints. Our algorithm uses local generators and discriminators which are periodically synced via an intermediary that averages and broadcasts the generator and discriminator parameters. We theoretically prove the convergence of FedGAN with both equal and two time-scale updates of generator and discriminator, under standard assumptions, using stochastic approximations and communication efficient stochastic gradient descents. We experiment FedGAN on toy examples (2D system, mixed Gaussian, and Swiss role), image datasets (MNIST, CIFAR-10, and CelebA), and time series datasets (household electricity consumption and electric vehicle charging sessions). We show FedGAN converges and has similar performance to general distributed GAN, while reduces communication complexity. We also show its robustness to reduced communications.

Mohammad Rasouli

System Dynamics (SD) main aim is to study dynamic behavior of systems based on causal relations. The other purpose of the science is to design policies, both in initial values and causal relation, to change system behavior as we desire. Especially we are interested in making systems behavior a convergent one. Although now SD is mainly used in situations of single policy maker, there are major parts of situations in which there are multi policy makers playing role. Game Theory (GT) is an appropriate tool for studying such cases.GT is the theory of studying multi decision-maker conditions. In this paper we will introduce GT and explain how to apply it in SD. Also we will provide some examples of microeconomic systems and show how to use GT for studying and simulating dynamics of these example systems. We will also have a short discuss on how SD can help GT studies.

Mohammad Rasouli, Erik Miehling, Demosthenis Teneketzis

An analytical approach for a dynamic cyber-security problem that captures progressive attacks to a computer network is presented. We formulate the dynamic security problem from the defender's point of view as a supervisory control problem with imperfect information, modeling the computer network's operation by a discrete event system. We consider a min-max performance criterion and use dynamic programming to determine, within a restricted set of policies, an optimal policy for the defender. We study and interpret the behavior of this optimal policy as we vary certain parameters of the supervisory control problem.