Static control systems get simpler rate cost tradeoff formulas
Single-Letterization of Rate-Cost Tradeoffs in Static Time-Invariant Control (STIC) Systems
Information Theory
Summary
Controlling complex systems often requires sending information through limited communication channels, which restricts how well the system can be controlled. The authors study a special category of control systems where the future only depends on the most recent action and doesn't change over time. They show that for these systems, the complicated mathematical relationship between communication rate and control quality can be simplified to a single equation that does not grow with time. This makes the problem of finding the best tradeoff easier to solve and understand.
What this means in practice
- •For online recommendation teams: Optimize data communication to improve recommendation quality under bandwidth constraints in static user behavior models.
- •For medical device engineers: Design communication-efficient control policies for devices that must act based only on limited interim patient data.
A theory result. No direct application yet.
Authors
Eray Unsal Atay, Venkat Chandrasekaran, Victoria Kostina
Abstract
In settings such as online recommendation platforms, medical decision-making with interim summaries, and stochastic control with static plants, the underlying system is often static so that the next state depends only on the most recent action. Moreover, the true system state is high-dimensional and cannot be observed directly, so actions must be selected based on information received through a rate-limited communication link, which constrains the control performance. This leads to a fundamental rate-cost tradeoff$\unicode{x2014}$the minimum communication rate required to achieve a prescribed average control cost. We study this tradeoff for a class of static systems we term static time-invariant control (STIC) systems, namely, control systems in which the next state depends on the history only through the most recent control action via a time-invariant kernel. For general control systems$\unicode{x2014}$not necessarily static or time-invariant$\unicode{x2014}$our prior work characterized this tradeoff through the limit of a sequence of directed-information minimization problems. However, the dimension of these problems grows with the time horizon, making the limiting formulation computationally intractable. In the present paper, we show for STIC systems that this growing-size formulation admits a single-letter characterization. This identifies STIC systems as the control-side counterpart of Noisy Output is the STate (NOST) channels$\unicode{x2014}$one of the few channel models whose feedback capacity admits a single-letter characterization. This yields, to our knowledge, the first constant-size convex characterization of the rate$\unicode{x2013}$cost tradeoff beyond linear quadratic Gaussian (LQG) control.