ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2202.04219
32
1
v1v2v3 (latest)

Improving Computational Complexity in Statistical Models with Second-Order Information

9 February 2022
Zhaolin Ren
Jiacheng Zhuo
Sujay Sanghavi
Nhat Ho
ArXiv (abs)PDFHTML
Abstract

It is known that when the statistical models are singular, i.e., the Fisher information matrix at the true parameter is degenerate, the fixed step-size gradient descent algorithm takes polynomial number of steps in terms of the sample size nnn to converge to a final statistical radius around the true parameter, which can be unsatisfactory for the application. To further improve that computational complexity, we consider the utilization of the second-order information in the design of optimization algorithms. Specifically, we study the normalized gradient descent (NormGD) algorithm for solving parameter estimation in parametric statistical models, which is a variant of gradient descent algorithm whose step size is scaled by the maximum eigenvalue of the Hessian matrix of the empirical loss function of statistical models. When the population loss function, i.e., the limit of the empirical loss function when nnn goes to infinity, is homogeneous in all directions, we demonstrate that the NormGD iterates reach a final statistical radius around the true parameter after a logarithmic number of iterations in terms of nnn. Therefore, for fixed dimension ddd, the NormGD algorithm achieves the optimal overall computational complexity O(n)\mathcal{O}(n)O(n) to reach the final statistical radius. This computational complexity is cheaper than that of the fixed step-size gradient descent algorithm, which is of the order O(nτ)\mathcal{O}(n^{\tau})O(nτ) for some τ>1\tau > 1τ>1, to reach the same statistical radius. We illustrate our general theory under two statistical models: generalized linear models and mixture models, and experimental results support our prediction with general theory.

View on arXiv
Comments on this paper