# Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization

arXiv: https://arxiv.org/abs/1406.3665 · HTML: https://mlsanity.com/paper/1406.3665/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2014.

## Built on by (most cited first, 6 of 6)

- [Learning to Transmit with Provable Guarantees in Wireless Federated Learning](https://mlsanity.com/paper/2304.09329/) (2023)
- [Context-Aware Doubly-Robust Semi-Supervised Learning](https://mlsanity.com/paper/2502.15577/) (2025)
- [Learning Multi-Frequency Partial Correlation Graphs](https://mlsanity.com/paper/2311.15756/) (2023)
- [CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks](https://mlsanity.com/paper/2509.19855/) (2025)
- [Fast MLE and MAPE-Based Device Activity Detection for Grant-Free Access via PSCA and PSCA-Net](https://mlsanity.com/paper/2503.15259/) (2025)
- [AltTS: A Dual-Path Framework with Alternating Optimization for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2602.11533/) (2026)

## Abstract (arXiv)

Consider the problem of minimizing the sum of a smooth (possibly non-convex) and a convex (possibly nonsmooth) function involving a large number of variables. A popular approach to solve this problem is the block coordinate descent (BCD) method whereby at each iteration only one variable block is updated while the remaining variables are held fixed. With the recent advances in the developments of the multi-core parallel processing technology, it is desirable to parallelize the BCD method by allowing multiple blocks to be updated simultaneously at each iteration of the algorithm. In this work, we propose an inexact parallel BCD approach where at each iteration, a subset of the variables is updated in parallel by minimizing convex approximations of the original objective function. We investigate the convergence of this parallel BCD method for both randomized and cyclic variable selection rules. We analyze the asymptotic and non-asymptotic convergence behavior of the algorithm for both convex and non-convex objective functions. The numerical experiments suggest that for a special case of Lasso minimization problem, the cyclic block selection rule can outperform the randomized rule.