DeepPursuit: Uniting Classical Wisdom and Deep RL for Sparse Recovery
DeepPursuit: Uniting Classical Wisdom and Deep RL for Sparse Recovery
复制标题
DOI：
10.1109/ieeeconf53345.2021.9723110
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Ziheng Chen;Sichen Zhong;Jianshu Chen;Yue Zhao
中科院分区：
文献类型：
--
作者：
Ziheng Chen;Sichen Zhong;Jianshu Chen;Yue Zhao
在本文中，我们将稀疏信号恢复描述为一个序列决策问题(由马尔可夫决策过程建模)。在此基础上，提出了一种新的稀疏恢复算法DeepPurSuit，它通过深度强化学习(RL)和蒙特卡罗树搜索(MCTS)学习恢复稀疏信号。为了显著提高学习速度和性能，DeepPurSuit(I)采用了一种新的残差型策略/价值网络结构，该结构有机地结合了正交匹配追踪(OMP)算法的经典智慧，以及(Ii)在训练过程中利用可用的基本事实知识来指导MCTS。对一般随机稀疏信号恢复的实验结果表明，DeepPurSuit算法在计算复杂度非常低的情况下，性能明显优于现有的算法。在MNIST数据集上的实验中观察到了更高的性能改进。
In this paper, we formulate sparse signal recovery as a sequential decision making problem (modeled by Markov Decision Processes). Based on the formulation, we propose DeepPursuit, a novel sparse recovery algorithm that learns to recover sparse signals via deep reinforcement learning (RL) and Monte Carlo Tree Search (MCTS). To substantially enhance the learning speed and performance, DeepPursuit (i) employs a novel residual-type policy/value network architecture that organically incorporates the classical wisdom from the Orthogonal Matching Pursuit (OMP) algorithm, and (ii) exploits the available ground-truth knowledge to guide the MCTS during the training process. Experimental results for general random sparse signal recovery demonstrate that, with very low computational complexity, the DeepPursuit algorithm significantly outperforms the state-of-the-art algorithms. Even higher performance gains are observed with experiments on the MNIST dataset.