Metraipolis › archive › dc_047f96229f19

Weak Convergence Rates for Partial-Sum Processes of Nonlinear Stochastic Approximation — arXiv:2609.40338

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40338
License (as archived)
CC0-1.0
Archived
2026-10-07T14:13:10.416Z
SHA-256 of the archived text
0abeb99dee483e4eb7e890dad96fd9b6f8bb297d1ba3829f04a612cb3d8705c3
Stable URL of this page
https://metraipolis.com/documento/dc_047f96229f19

How to cite

Weak Convergence Rates for Partial-Sum Processes of Nonlinear Stochastic Approximation — arXiv:2609.40338 — arXiv (en), https://arxiv.org/abs/2609.40338 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_047f96229f19 (Metraipolis archive dc_047f96229f19, sha256 0abeb99dee483e4eb7e890dad96fd9b6f8bb297d1ba3829f04a612cb3d8705c3)
BibTeX
@misc{dc047f96229f19,
  title = {Weak Convergence Rates for Partial-Sum Processes of Nonlinear Stochastic Approximation — arXiv:2609.40338},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40338},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_047f96229f19; sha256 0abeb99dee483e4eb7e890dad96fd9b6f8bb297d1ba3829f04a612cb3d8705c3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40338. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Stochastic approximation provides a general framework for online estimation and optimization. Statistical inference based on the resulting estimates requires understanding their fluctuations around the target. For Polyak--Ruppert averaging, functional central limit theorems describe the normalized cumulative estimation errors through a Brownian limit. However, weak convergence alone does not determine how quickly the distribution of this process approaches that limit. We establish a quantitative functional central limit theorem for nonlinear stochastic approximation with polynomially decreasing step sizes and martingale-difference noise. Under suitable regularity and moment conditions, we derive an explicit finite-sample bound on the Prokhorov distance between each fixed scalar projection of the normalized partial-sum process and its Brownian limit. The bound reveals a step-size tradeoff: faster step-size decay reduces the contribution of the nonlinear remainder but increases that of the smoothing induced by the recursion. To assess the sharpness of the upper bound, we develop four lower-bound constructions, each designed to isolate one source of error. They show that covariance stabilization, finite-moment noise, algorithmic smoothing, and nonlinearity can each separately limit the Brownian approximation rate of the SA path.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-01 in math.ST).
Categorie arXiv: Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.40338 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T14:03:45.745Z dalla pagina https://arxiv.org/catchup/math.ST/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).