no code implementations • 10 Nov 2023 • Yves Atchade, Xinru Liu, Qiuyun Zhu
We show that the unrolling depth needed for the optimal statistical performance of GDNs is of order $\log(n)/\log(\varrho_n^{-1})$, where $n$ is the sample size, and $\varrho_n$ is the convergence rate of the corresponding gradient descent algorithm.
1 code implementation • 16 Oct 2020 • Qiuyun Zhu, Yves Atchade
The method builds on Tan et al. (2018) and uses a re-scaled Rayleigh quotient function as the quasi-log-likelihood.