.png){kind=icon}
.png){kind=icon}
Return
Metalearning-Based Alternating Minimization Algorithm for Nonconvex Optimization
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2022.3165627.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this article, we propose a novel solution for nonconvex problems of multiple variables, especially for those typically solved by an alternating minimization (AM) strategy that splits the original optimization problem into a set of subproblems corresponding to each variable and then iteratively optimizes each subproblem using a fixed updating rule. However, due to the intrinsic nonconvexity of the original optimization problem, the optimization can be trapped into a spurious local minimum even when each subproblem can be optimally solved at each iteration. Meanwhile, learning-based approaches, such as deep unfolding algorithms, have gained popularity for nonconvex optimization; however, they are highly limited by the availability of labeled data and insufficient explainability. To tackle these issues, we propose a meta-learning based alternating minimization (MLAM) method that aims to minimize a part of the global losses over iterations instead of carrying minimization on each subproblem, and it tends to learn an adaptive strategy to replace the handcrafted counterpart resulting in advance on superior performance. The proposed MLAM maintains the original algorithmic principle, providing certain interpretability. We evaluate the proposed method on two representative problems, namely, bilinear inverse problem: matrix completion and nonlinear problem: Gaussian mixture models. The experimental results validate the proposed approach outperforms AM-based methods.
Keywords:
Optimization
Minimization
Task analysis
Deep learning
Neural networks
Signal processing algorithms
Iterative algorithms
Alternating minimization (AM)
deep unfolding
gaussian mixture model (GMM)
matrix completion
meta-learning (ML)
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W
Organization
View more organizations