English

Error Estimate and Convergence Analysis for Data Valuation

Machine Learning 2025-12-19 v3

Abstract

Data valuation quantifies data importance, but existing methods cannot ensure validity in a single training process. The neural dynamic data valuation (NDDV) method [3] addresses this limitation. Based on NDDV, we are the first to explore error estimation and convergence analysis in data valuation. Under Lipschitz and smoothness assumptions, we derive quadratic error bounds for loss differences that scale inversely with time steps and quadratically with control variations, ensuring stability. We also prove that the expected squared gradient norm for the training loss vanishes asymptotically, and that the meta loss converges sublinearly over iterations. In particular, NDDV achieves sublinear convergence.

Keywords

Cite

@article{arxiv.2511.06463,
  title  = {Error Estimate and Convergence Analysis for Data Valuation},
  author = {Zhangyong Liang and Huanhuan Gao and Ji Zhang},
  journal= {arXiv preprint arXiv:2511.06463},
  year   = {2025}
}

Comments

7 pages, 3 figure

R2 v1 2026-07-01T07:28:29.144Z