# PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent

arXiv: https://arxiv.org/abs/1504.01365 · HTML: https://mlsanity.com/paper/1504.01365/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2015.

## Built on by (most cited first, 4 of 4)

- [Distributed Learning Systems with First-order Methods](https://mlsanity.com/paper/2104.05245/) (2021)
- [Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout](https://mlsanity.com/paper/2210.16105/) (2022)
- [Scaling up Stochastic Gradient Descent for Non-convex Optimisation](https://mlsanity.com/paper/2210.02882/) (2022)
- [Distributed Dual Coordinate Ascent with Imbalanced Data on a General Tree Network](https://mlsanity.com/paper/2308.14783/) (2023)

## Abstract (arXiv)

Stochastic Dual Coordinate Descent (SDCD) has become one of the most efficient ways to solve the family of ℓ2-regularized empirical risk minimization problems, including linear SVM, logistic regression, and many others. The vanilla implementation of DCD is quite slow; however, by maintaining primal variables while updating dual variables, the time complexity of SDCD can be significantly reduced. Such a strategy forms the core algorithm in the widely-used LIBLINEAR package. In this paper, we parallelize the SDCD algorithms in LIBLINEAR. In recent research, several synchronized parallel SDCD algorithms have been proposed, however, they fail to achieve good speedup in the shared memory multi-core setting. In this paper, we propose a family of asynchronous stochastic dual coordinate descent algorithms (ASDCD). Each thread repeatedly selects a random dual variable and conducts coordinate updates using the primal variables that are stored in the shared memory. We analyze the convergence properties when different locking/atomic mechanisms are applied. For implementation with atomic operations, we show linear convergence under mild conditions. For implementation without any atomic operations or locking, we present the first it backward error analysis for ASDCD under the multi-core environment, showing that the converged solution is the exact solution for a primal problem with perturbed regularizer. Experimental results show that our methods are much faster than previous parallel coordinate descent solvers.