Inexact Block Coordinate Descent Algorithms for Nonsmooth Nonconvex Optimization

E-print/Working paper (2019)

In this paper, we propose an inexact block coordinate descent algorithm for large-scale nonsmooth nonconvex optimization problems. At each iteration, a particular block variable is selected and updated by ... [more ▼]

In this paper, we propose an inexact block coordinate descent algorithm for large-scale nonsmooth nonconvex optimization problems. At each iteration, a particular block variable is selected and updated by solving the original optimization problem with respect to that block variable inexactly. More precisely, a local approximation of the original optimization problem is solved. The proposed algorithm has several attractive features, namely, i) high flexibility, as the approximation function only needs to be strictly convex and it does not have to be a global upper bound of the original function; ii) fast convergence, as the approximation function can be designed to exploit the problem structure at hand and the stepsize is calculated by the line search; iii) low complexity, as the approximation subproblems are much easier to solve and the line search scheme is carried out over a properly constructed differentiable function; iv) guaranteed convergence to a stationary point, even when the objective function does not have a Lipschitz continuous gradient. Interestingly, when the approximation subproblem is solved by a descent algorithm, convergence to a stationary point is still guaranteed even if the approximation subproblem is solved inexactly by terminating the descent algorithm after a finite number of iterations. These features make the proposed algorithm suitable for large-scale problems where the dimension exceeds the memory and/or the processing capability of the existing hardware. These features are also illustrated by several applications in signal processing and machine learning, for instance, network anomaly detection and phase retrieval. [less ▲]

Power and Load Optimization in Interference-Coupled Non-Orthogonal Multiple Access Networks

in IEEE Global Communications Conference (GLOBECOM) 2018 (2018, December)

Parallel and hybrid soft-thresholding algorithms with line search for sparse nonlinear regression

in Proc. 26th European Signal Processing Conference (2018, September)

Successive convex approximation algorithms for sparse signal estimation with nonconvex regularizations

in Proc. The 10th IEEE Sensor Array and Multichannel Signal Processing Workshop (2018, July)

Optimization of weighted individual energy efficiencies in interference networks

in Proc. IEEE Wireless Communications and Networking Conference (2018, April)

A parallel best-response algorithm with exact line search for nonconvex sparsity-regularized rank minimization

in Proc. 2018 IEEE International Conference on Acoustics, Speech and Signal (2018, April)

Energy efficient transmission in MIMO interference channels with QoS constraints

in Proc. 8th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (2017, December)

A unified successive pseudoconvex approximation framework

in IEEE Transactions on Signal Processing (2017), 65(13), 3313-3328

Multidimensional sparse recovery for MIMO channel parameter estimation

in Proc. 24th European Signal Processing Conference (2016, August)

A parallel decomposition method for nonconvex stochastic multi-agent optimization problems

in IEEE Transactions on Signal Processing (2016), 64(11), 2949-2964