CISPA
Browse

Optimizing (L0,L1)-Smooth Functions by Gradient Methods

Download (603.4 kB)
conference contribution
posted on 2025-04-28, 13:43 authored by Daniil Vankov, Anton RodomanovAnton Rodomanov, Angelia Nedich, Lalitha Sankar, Sebastian StichSebastian Stich
WWe study gradient methods for solving an optimization problem with an (L0,L1)-smooth objective function. This problem class generalizes that of Lipschitz-smooth problems and has gained interest recently, as it captures a broader range of machine learning applications. We provide novel insights on the properties of this function class and develop a general framework for analyzing optimization methods for (L0,L1)-smooth function in a principled manner. While our convergence rate estimates recover existing results for minimizing the gradient norm for nonconvex problems, our approach allows us to significantly improve the current state-of-the-art complexity results in the case of convex problems. We show that both the gradient method with Polyak stepsizes and the normalized gradient method, without any knowledge of the parameters L0 and L1, achieve the same complexity bounds as the method with the knowledge of these constants. In addition to that, we show that a carefully chosen accelerated gradient method can be applied to (L0,L1)-smooth functions, further improving previously known results. In all cases, the efficiency bounds we establish do not have an exponential dependency on L0 or L1, and do not depend on the initial gradient norm.

History

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

International Conference on Learning Representations (ICLR)

CISPA Affiliation

  • Yes

Open Access Type

  • Unknown

BibTeX

@conference{Vankov:Rodomanov:Nedich:Sankar:Stich:2024, title = "Optimizing (L0,L1)-Smooth Functions by Gradient Methods", author = "Vankov, Daniil" AND "Rodomanov, Anton" AND "Nedich, Angelia" AND "Sankar, Lalitha" AND "Stich, Sebastian", year = 2024, month = 10, doi = "10.48550/arXiv.2410.10800" }

Usage metrics

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC