# Inexact Block Coordinate Descent Algorithms for Nonsmooth Nonconvex Optimization

arXiv: https://arxiv.org/abs/1905.04211 · HTML: https://mlsanity.com/paper/1905.04211/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2019.

## Built on by (most cited first, 12 of 12)

- [CoLiDE: Concomitant Linear DAG Estimation](https://mlsanity.com/paper/2310.02895/) (2023)
- [NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning](https://mlsanity.com/paper/2403.06828/) (2024)
- [Learned Alternating Minimization Algorithm for Dual-domain Sparse-View CT Reconstruction](https://mlsanity.com/paper/2306.02644/) (2023)
- [Efficient Learning of Decision-Making Models: A Penalty Block Coordinate Descent Algorithm for Data-Driven Inverse Optimization](https://mlsanity.com/paper/2210.15393/) (2022)
- [Concomitant DAG Learning: On the Roles of Noise Adaptivity, Sparsity, and Non-negativity](https://mlsanity.com/paper/2605.23537/) (2026)
- [Learn for Variation: Efficient AAV Trajectory Learning through a Differentiable Wireless World Model](https://mlsanity.com/paper/2603.18853/) (2026)
- [Adaptive Anomaly Detection in Network Flows with Low-Rank Tensor Decompositions and Deep Unrolling](https://mlsanity.com/paper/2409.11529/) (2024)
- [Fast Equivariant Imaging: Accelerating Unsupervised Learning and Model Adaptation via Inexact Splitting](https://mlsanity.com/paper/2507.06764/) (2025)
- [Learning to Gridize: Segment Physical World by Wireless Communication Channel](https://mlsanity.com/paper/2507.15386/) (2025)
- [Accelerating Wireless Distributed Learning via Hybrid Split and Federated Learning Optimization](https://mlsanity.com/paper/2511.19851/) (2025)
- [Sparse Network Inference under Imperfect Detection and its Application to Ecological Networks](https://mlsanity.com/paper/2604.18820/) (2026)
- [Nonnegative DAG Learning via Concomitant Estimation](https://mlsanity.com/paper/2609.34595/) (2026)

## Abstract (arXiv)

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 inexactly solving the original optimization problem with respect to that block variable. 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 of a subsequence 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 of a subsequence 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.