Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression

Abstract

In this paper, we consider supervised learning problems such as logistic regression and study the stochastic gradient method with averaging, in the usual stochastic approximation setting where observations are used only once. We show that after $N$ iterations, with a constant step-size proportional to $1/R^2\sqrt{N}$ where $N$ is the number of observations and $R$ is the maximum norm of the observations, the convergence rate is always of order $O(1/\sqrt{N})$, and improves to $O(R^2/\mu N)$ where $\mu$ is the lowest eigenvalue of the Hessian at the global optimum (when this eigenvalue is greater than $R^2/\sqrt{N}$). Since $\mu$ does not need to be known in advance, this shows that averaged stochastic gradient is adaptive to \emph{unknown local} strong convexity of the objective function. Our proof relies on the generalized self-concordance properties of the logistic loss and thus extends to all generalized linear models with uniformly bounded features.

Cited by in corpus (6)

• Stochastic Successive Convex Approximation for Non-Convex Constrained Stochastic Optimization
• Proximity Without Consensus in Online Multi-Agent Optimization
• Strong error analysis for stochastic gradient descent optimization algorithms
• DC-DistADMM: ADMM Algorithm for Constrained Distributed Optimization over Directed Graphs
• Non asymptotic analysis of Adaptive stochastic gradient algorithms and applications
• Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms