arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07983cs.ITmath.IT
收藏

大字母Ising信道反馈容量的强化学习评估与求解

Reinforcement Learning Evaluation and Solution for the Feedback Capacity of the Ising Channel with Large Alphabet

Ziv Aharoni, Oron Sabag, Haim Henri Permuter

摘要:

提出了一种利用强化学习(RL)计算单股有限状态信道反馈容量的新方法。反馈能力是以前估计使用其配方作为一个马尔可夫决策过程(MDP)与动态规划(DP)算法。然而,它们的计算复杂性随着信道字母表的大小呈指数增长。因此,我们使用RL,特别是它的能力,参数化价值函数和政策与神经网络,数字评估的反馈能力的信道具有较大的字母大小。RL算法的结果是反馈能力的数值下界,其用于揭示最优解的结构。该结构由一个基于图的辅助随机变量来建模,该辅助随机变量被用来推导具有对偶界的反馈容量的解析上界。容量计算的结论是通过测试是否是BCJR不变的上限验证的紧密性。我们证明了这种方法的伊辛通道与任意字母大小。对于小于或等于8的字母表大小,我们推导出容量的解析解。接下来,数值解的结构被用来推导出一个简单的编码方案,实现了反馈能力,并作为一个更大的字母的下限。对于大于8的字母表大小,我们提出了一个上界的反馈能力。对于一个渐近大的字母大小,我们提出了一个渐近最优编码方案。

英文摘要:

We propose a new method to compute the feedback capacity of unifilar finite state channels (FSCs) with memory using reinforcement learning (RL). The feedback capacity was previously estimated using its formulation as a Markov decision process (MDP) with dynamic programming (DP) algorithms. However, their computational complexity grows exponentially with the channel alphabet size. Therefore, we use RL, and specifically its ability to parameterize value functions and policies with neural networks, to evaluate numerically the feedback capacity of channels with a large alphabet size. The outcome of the RL algorithm is a numerical lower bound on the feedback capacity, which is used to reveal the structure of the optimal solution. The structure is modeled by a graph-based auxiliary random variable that is utilized to derive an analytic upper bound on the feedback capacity with the duality bound. The capacity computation is concluded by verifying the tightness of the upper bound by testing whether it is BCJR invariant. We demonstrate this method on the Ising channel with an arbitrary alphabet size. For an alphabet size smaller than or equal to 8, we derive the analytic solution of the capacity. Next, the structure of the numerical solution is used to deduce a simple coding scheme that achieves the feedback capacity and serves as a lower bound for larger alphabets. For an alphabet size greater than 8, we present an upper bound on the feedback capacity. For an asymptotically large alphabet size, we present an asymptotic optimal coding scheme.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑