# SDCA without Duality, Regularization, and Individual Convexity

arXiv: https://arxiv.org/abs/1602.01582 · HTML: https://mlsanity.com/paper/1602.01582/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2016.

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

- [Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization](https://mlsanity.com/paper/2302.04552/) (2023)
- [Stochastic Polyak Stepsize with a Moving Target](https://mlsanity.com/paper/2106.11851/) (2021)
- [Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence](https://mlsanity.com/paper/2204.09266/) (2022)
- [Quantum Algorithms and Lower Bounds for Finite-Sum Optimization](https://mlsanity.com/paper/2406.03006/) (2024)

## Abstract (arXiv)

Stochastic Dual Coordinate Ascent is a popular method for solving regularized loss minimization for the case of convex losses. We describe variants of SDCA that do not require explicit regularization and do not rely on duality. We prove linear convergence rates even if individual loss functions are non-convex, as long as the expected loss is strongly convex.