# On the convergence of gradient-like flows with noisy gradient input

arXiv: https://arxiv.org/abs/1611.06730 · HTML: https://mlsanity.com/paper/1611.06730/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2016.

## Built on by (most cited first, 7 of 7)

- [Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium](https://mlsanity.com/paper/2104.12761/) (2021)
- [Learning in nonatomic games, Part I: Finite action spaces and population games](https://mlsanity.com/paper/2107.01595/) (2021)
- [Zeroth-order non-convex learning via hierarchical dual averaging](https://mlsanity.com/paper/2109.05829/) (2021)
- [First-Order Methods for Convex Optimization](https://mlsanity.com/paper/2101.00935/) (2021)
- [The impact of uncertainty on regularized learning in games](https://mlsanity.com/paper/2506.13286/) (2025)
- [Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective](https://mlsanity.com/paper/2603.03226/) (2026)
- [Multi-agent learning under uncertainty: Recurrence vs. concentration](https://mlsanity.com/paper/2512.08132/) (2025)

## Abstract (arXiv)

In view of solving convex optimization problems with noisy gradient input, we analyze the asymptotic behavior of gradient-like flows under stochastic disturbances. Specifically, we focus on the widely studied class of mirror descent schemes for convex programs with compact feasible regions, and we examine the dynamics' convergence and concentration properties in the presence of noise. In the vanishing noise limit, we show that the dynamics converge to the solution set of the underlying problem (a.s.). Otherwise, when the noise is persistent, we show that the dynamics are concentrated around interior solutions in the long run, and they converge to boundary solutions that are sufficiently "sharp". Finally, we show that a suitably rectified variant of the method converges irrespective of the magnitude of the noise (or the structure of the underlying convex program), and we derive an explicit estimate for its rate of convergence.