Work

AccSPS Learning Rate: Accelerated Convergence Through Decision-Adjusted Levels for Stochastic Polyak Stepsize

Year: 2025

Type: article

Source: IEEE Transactions on Automation Science and Engineering

DOI: 10.1109/tase.2025.3613719

Authors: Jingtao Qin, Anbang Liu, Mikhail A. Bragin, Nanpeng Yu

Institutions: University of California, Riverside, University of Hong Kong, Edison International (United States)

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funder: National Science Foundation

Award: DESC: Type I: Minimizing Carbon Footprint by Co-designing Data Centers with Sustainable Power Grids

OpenAlex ID: W7083179631

FWCI:

Cites: 19

Cited by:

Related to: