Simultaneous perturbation stochastic approximation: towards one-measurement per iteration
Not on the map. Why?
Abstract (arXiv)
When measuring the value of a function to be minimized is not only expensive but also with noise, the popular simultaneous perturbation stochastic approximation (SPSA) algorithm requires only two function values in each iteration. In this paper, we propose a method requiring only one function measurement value per iteration in the average sense. We prove the strong convergence and asymptotic normality of the new algorithm. Experimental results show the effectiveness and potential of our algorithm.
Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Mar 2022.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 2; 2024: 1; 2025: 1.
4 papers.
- 2023Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applicationscited by 15
- 2024MINI-LLM: Memory-Efficient Structured Pruning for Large Language Modelscited by 5
- 2023Convergence of the Stochastic Heavy Ball Method With Approximate Gradients and/or Block Updatingcited by 2
- 2025Revisiting Stochastic Approximation and Stochastic Gradient Descentcited by 0
- 2025Revisiting Stochastic Approximation and Stochastic Gradient Descent16 May 2025
- 2024MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models16 Jul 2024
- 2023Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications5 Dec 2023
- 2023Convergence of the Stochastic Heavy Ball Method With Approximate Gradients and/or Block Updating28 Mar 2023