Finding a computable expression for the feedback capacity of channels with colored Gaussian, additive noise is a long standing open problem. In this paper, we solve this problem in the scenario where the channel has multiple inputs and multiple outputs (MIMO) and the noise process is generated as the output of a time-invariant state-space model. Our main result is a computable expression for the feedback capacity in terms of a finite-dimensional convex optimization. The solution to the feedback capacity problem is obtained by formulating the finite-block counterpart of the capacity problem as a \emph{sequential convex optimization problem} which leads in turn to a single-letter upper bound. This converse derivation integrates tools and ideas from information theory, control, filtering and convex optimization. A tight lower bound is realized by optimizing over a family of time-invariant policies thus showing that time-invariant inputs are optimal even when the noise process may not be stationary. The optimal time-invariant policy is used to construct a capacity-achieving and simple coding scheme for scalar channels, and its analysis reveals an interesting relation between a smoothing problem and the feedback capacity expression.
翻译:以彩色高斯语言查找频道反馈能力的可比较表达式, 添加噪声是一个长期的开放问题。 在本文中, 我们解决了这个问题, 假设频道有多个输入和多个输出( MIMO), 噪音过程是作为时间变化状态- 空间模型的输出生成的。 我们的主要结果就是以有限维共性优化的方式对反馈能力进行可比较表达。 反馈能力问题的解决方案是通过将能力问题作为 \ emph{ 序列 convex 优化问题} 的有限区对应方进行配置而获得的。 而这又导致一个单字母的上线 。 这种对等导出将信息理论、 控制、 过滤和 convex 优化产生的工具和想法整合为时间变化状态- 模型的输出。 通过优化一个时间变化状态政策组合实现一个更窄的下限值。 这表明, 即使在噪音进程可能不固定的情况下, 时间变量输入也是最理想的。 最佳的时间变量政策被用来构建一个能力化和简单 Coding sal reful reful reful reful reful reful 关系 。