English

Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates

Optimization and Control 2026-04-15 v2 Machine Learning

Abstract

Achieving optimal rates for stochastic composite convex optimization without prior knowledge of problem parameters remains a central challenge. In the deterministic setting, the auto-conditioned fast gradient method has recently been proposed to attain optimal accelerated rates without line-search procedures or prior knowledge of the Lipschitz smoothness constant, providing a natural prototype for parameter-free acceleration. However, extending this approach to the stochastic setting has proven technically challenging and remains open. Existing parameter-free stochastic methods either fail to achieve accelerated rates or rely on restrictive assumptions, such as bounded domains, bounded gradients, prior knowledge of the iteration horizon, or strictly sub-Gaussian noise. To address these limitations, we propose a stochastic variant of the auto-conditioned fast gradient method, referred to as stochastic AC-FGM. The proposed method is fully adaptive to the Lipschitz constant, the iteration horizon, and the noise level, enabling both adaptive stepsize selection and adaptive mini-batch sizing without line-search procedures. Under standard bounded conditional variance assumptions, we show that stochastic AC-FGM achieves the optimal iteration complexity of O(1/ε)O(1/\sqrt{\varepsilon}) and the optimal sample complexity of O(1/ε2)O(1/\varepsilon^2).

Keywords

Cite

@article{arxiv.2604.06525,
  title  = {Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates},
  author = {Yao Ji and Guanghui Lan},
  journal= {arXiv preprint arXiv:2604.06525},
  year   = {2026}
}
R2 v1 2026-07-01T11:58:26.119Z