DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning. (arXiv:2201.08477v1 [eess.SP])

Web: http://arxiv.org/abs/2201.08477

Deep-unfolding neural networks (NNs) have received great attention since they
achieve satisfactory performance with relatively low complexity. Typically,
these deep-unfolding NNs are restricted to a fixed-depth for all inputs.
However, the optimal number of layers required for convergence changes with
different inputs. In this paper, we first develop a framework of deep
deterministic policy gradient (DDPG)-driven deep-unfolding with adaptive depth
for different inputs, where the trainable parameters of deep-unfolding NN are
learned by DDPG, rather than updated by the stochastic …

arxiv bayesian deep learning