An Iterative Discrete Least Square Estimator with Dynamic Parameterization via Deep-Unfolding
- Resource Type
- Conference
- Authors
- Ando, Kengo; Iimori, Hiroki; Rou, Hyeon Seok; Freitas de Abreu, Giuseppe Thadeu; G, David Gonzalez; Gonsa, Osvaldo
- Source
- 2022 56th Asilomar Conference on Signals, Systems, and Computers Signals, Systems, and Computers, 2022 56th Asilomar Conference on. :32-36 Oct, 2022
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Fields, Waves and Electromagnetics
Signal Processing and Analysis
Linear systems
Deep learning
Heuristic algorithms
Computer simulation
Neural networks
Symbols
Market research
Discrete inversion
deep unfolding
least square
multidimensional linear systems
- Language
- ISSN
- 2576-2303
We propose a new dynamic parameterization approach via deep unfolding as an extension of the recently-introduced iterative discrete least square (IDLS) scheme, shown to elegantly generalize the conventional linear minimum mean squared error (LMMSE) method to enable the solution of inversion problems in complex multidimensional linear systems subject to discrete inputs. Configuring a layer-wise structure analogous to a deep neural network, the new approach enables an efficient optimization of the iterative IDLS algorithm, by finding optimal hyper-parameters for the related optimization problem through backpropagation and stochastic gradient descent techniques. The effectiveness of the proposed approach is confirmed via computer simulations.