Zero-Delay Lossy Coding of Linear Vector Markov Sources: Optimality of Stationary Codes and Near Optimality of Finite Memory Codes

03/19/2021

∙

Optimal zero-delay coding (quantization) of ℝ^d-valued linearly generated Markov sources is studied under quadratic distortion. The structure and existence of deterministic and stationary coding policies that are optimal for the infinite horizon average cost (distortion) problem is established. Prior results studying the optimality of zero-delay codes for Markov sources for infinite horizons either considered finite alphabet sources or, for the ℝ^d-valued case, only showed the existence of deterministic and non-stationary Markov coding policies or those which are randomized. In addition to existence results, for finite blocklength (horizon) T the performance of an optimal coding policy is shown to approach the infinite time horizon optimum at a rate O(1/T). This gives an explicit rate of convergence that quantifies the near-optimality of finite window (finite-memory) codes among all optimal zero-delay codes.

READ FULL TEXT

Zero-Delay Lossy Coding of Linear Vector Markov Sources: Optimality of Stationary Codes and Near Optimality of Finite Memory Codes

Zero-Delay Rate Distortion via Filtering for Vector-Valued Gaussian Sources

On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes

On Zero-Delay RDF for Vector-Valued Gauss-Markov Sources with Additional Noise

A Converse Bound Characterization on Zero-Delay Indirect RDF for Vector Gauss-Markov Sources

Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes

Optimal Causal Rate-Constrained Sampling of the Wiener Process

Convergence of Finite Memory Q-Learning for POMDPs and Near Optimality of Learned Policies under Filter Stability

Zero-Delay Lossy Coding of Linear Vector Markov Sources: Optimality of Stationary Codes and Near Optimality of Finite Memory Codes

Related Research

Zero-Delay Rate Distortion via Filtering for Vector-Valued Gaussian Sources

On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes

On Zero-Delay RDF for Vector-Valued Gauss-Markov Sources with Additional Noise

A Converse Bound Characterization on Zero-Delay Indirect RDF for Vector Gauss-Markov Sources

Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes

Optimal Causal Rate-Constrained Sampling of the Wiener Process

Convergence of Finite Memory Q-Learning for POMDPs and Near Optimality of Learned Policies under Filter Stability