Skip to Main content Skip to Navigation
Conference papers

Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions

Abstract : We provide a novel computer-assisted technique for systematically analyzing first-order methods for optimization. In contrast with previous works, the approach is particularly suited for handling sublinear convergence rates and stochastic oracles. The technique relies on semidefinite programming and potential functions. It allows simultaneously obtaining worst-case guarantees on the behavior of those algorithms, and assisting in choosing appropriate parameters for tuning their worst-case performances. The technique also benefits from comfortable tightness guarantees, meaning that unsatisfactory results can be improved only by changing the setting. We use the approach for analyzing deterministic and stochastic first-order methods under different assumptions on the nature of the stochastic noise. Among others, we treat unstructured noise with bounded variance, different noise models arising in over-parametrized expectation minimization problems, and randomized block-coordinate descent schemes.
Complete list of metadata
Contributor : Adrien Taylor Connect in order to contact the contributor
Submitted on : Wednesday, February 6, 2019 - 11:42:29 AM
Last modification on : Thursday, March 17, 2022 - 10:08:53 AM

Links full text


  • HAL Id : hal-02009309, version 1
  • ARXIV : 1902.00947



Adrien Taylor, Francis Bach. Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions. COLT 2019 - Conference on Learning Theory, Jun 2019, Phoenix, United States. ⟨hal-02009309⟩



Record views