An information-theoretic analysis of nonstationary bandit learning
In nonstationary bandit learning problems, the decision-maker must continually gather
information and adapt their action selection as the latent state of the environment evolves. In …
information and adapt their action selection as the latent state of the environment evolves. In …
Effective Communication with Dynamic Feature Compression
The remote wireless control of industrial systems is one of the major use cases for 5G and
beyond systems: in these cases, the massive amounts of sensory information that need to be …
beyond systems: in these cases, the massive amounts of sensory information that need to be …
Minimum bitrate neuromorphic encoding for continuous-time gauss-markov processes
T Cuvelier, R Ogden, T Tanaka - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
In this work, we study minimum data rate tracking of a dynamical system under a
neuromorphic event-based sensing paradigm. We begin by bridging the gap between …
neuromorphic event-based sensing paradigm. We begin by bridging the gap between …
The time-invariant multidimensional Gaussian sequential rate-distortion problem revisited
PA Stavrou, T Tanaka… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
We revisit the sequential rate-distortion (SRD) tradeoff problem for vector-valued Gauss-
Markov sources with mean-squared error distortion constraints. Our study is partly motivated …
Markov sources with mean-squared error distortion constraints. Our study is partly motivated …
Reinforcement Learning for Near-Optimal Design of Zero-Delay Codes for Markov Sources
In the classical lossy source coding problem, one encodes long blocks of source symbols
that enables the distortion to approach the ultimate Shannon limit. Such a blockcoding …
that enables the distortion to approach the ultimate Shannon limit. Such a blockcoding …
Time-invariant prefix coding for LQG control
TC Cuvelier, T Tanaka… - IEEE Journal on Selected …, 2022 - ieeexplore.ieee.org
Motivated by control with communication constraints, in this work we develop a time-
invariant data compression architecture for linear-quadratic-Gaussian (LQG) control with …
invariant data compression architecture for linear-quadratic-Gaussian (LQG) control with …
Zero-delay lossy coding of linear vector Markov sources: Optimality of stationary codes and near optimality of finite memory codes
Optimal zero-delay coding (quantization) of-valued linearly generated Markov sources is
studied under quadratic distortion. The structure and existence of deterministic and …
studied under quadratic distortion. The structure and existence of deterministic and …
Sequential source coding for stochastic systems subject to finite rate constraints
PA Stavrou, M Skoglund… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In this article, we revisit the sequential source-coding framework to analyze fundamental
performance limitations of discrete-time stochastic control systems subject to feedback data …
performance limitations of discrete-time stochastic control systems subject to feedback data …
Asymptotic reverse waterfilling algorithm of NRDF for certain classes of vector Gauss–Markov processes
PA Stavrou, M Skoglund - IEEE Transactions on Automatic …, 2021 - ieeexplore.ieee.org
The existence of an optimal reverse-waterfilling algorithm to compute the nonanticipative
rate distortion function (NRDF) for time-invariant vector-valued Gauss–Markov processes …
rate distortion function (NRDF) for time-invariant vector-valued Gauss–Markov processes …
Decentralized inference and its application to network localization and navigation
Z Liu - 2022 - oastats.mit.edu
Decentralized inference is important for complex networked systems and enables numerous
applications such as network localization and navigation (NLN), Internet-ofThings (IoT), and …
applications such as network localization and navigation (NLN), Internet-ofThings (IoT), and …