Asymptotic and finite-sample properties of estimators based on stochastic gradients (Q2403434): Difference between revisions

This paper deals with implicit stochastic gradient descent procedures, defined as \(\Theta^{im}_n=\Theta^{im}_{n-1}+\nu_n\nabla\log f(Y_{ni}X_n,\Theta^{im}_n)\), where \(\nu_n>0\) is the learning rate sequence, typically \(\nu_n:=\nu_1 n^{-\nu}\), \(\nu_1>0\) is the learning rate parameter, \(\nu_n\in(0. 5,1]\), and \(C_n\) are \(p\times p\) positive definite matrices, also known as condition matrices. The authors' ``theoretical analysis provides the first full characterization of the behavior of both standard and implicit stochastic gradient descent-based estimators, including finite-sample error bounds''.