# Online Stochastic Gradient Methods Under Sub-Weibull Noise and the Polyak-Lojasiewicz Condition

arXiv: https://arxiv.org/abs/2108.03285 · HTML: https://mlsanity.com/paper/2108.03285/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2021.

## Built on by (most cited first, 3 of 3)

- [General Tail Bounds for Non-Smooth Stochastic Mirror Descent](https://mlsanity.com/paper/2312.07142/) (2023)
- [Distributionally Time-Varying Online Stochastic Optimization under Polyak-Lojasiewicz Condition with Application in Conditional Value-at-Risk Statistical Learning](https://mlsanity.com/paper/2309.09411/) (2023)
- [Online Non-Stationary Stochastic Quasar-Convex Optimization](https://mlsanity.com/paper/2407.03601/) (2024)

## Abstract (arXiv)

This paper focuses on the online gradient and proximal-gradient methods with stochastic gradient errors. In particular, we examine the performance of the online gradient descent method when the cost satisfies the Polyak-L ojasiewicz (PL) inequality. We provide bounds in expectation and in high probability (that hold iteration-wise), with the latter derived by leveraging a sub-Weibull model for the errors affecting the gradient. The convergence results show that the instantaneous regret converges linearly up to an error that depends on the variability of the problem and the statistics of the sub-Weibull gradient error. Similar convergence results are then provided for the online proximal-gradient method, under the assumption that the composite cost satisfies the proximal-PL condition. In the case of static costs, we provide new bounds for the regret incurred by these methods when the gradient errors are modeled as sub-Weibull random variables. Illustrative simulations are provided to corroborate the technical findings.