Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression
From MaRDI portal
Publication:2934003
zbMath1318.62224arXiv1303.6149MaRDI QIDQ2934003
Publication date: 8 December 2014
Full work available at URL: https://arxiv.org/abs/1303.6149
Related Items
Lp and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective, Some Limit Properties of Markov Chains Induced by Recursive Stochastic Algorithms, Inversion-free subsampling Newton's method for large sample logistic regression, Streaming constrained binary logistic regression with online standardized data, Unnamed Item, Approximate maximum likelihood estimation for population genetic inference, Semi-discrete optimal transport: hardness, regularization and numerical solution, Convergence of the exponentiated gradient method with Armijo line search, Optimal non-asymptotic analysis of the Ruppert-Polyak averaging stochastic algorithm, Adaptive step size rules for stochastic optimization in large-scale learning, Unnamed Item, Composite Convex Minimization Involving Self-concordant-Like Cost Functions, On the rates of convergence of parallelized averaged stochastic gradient algorithms, Bridging the gap between constant step size stochastic gradient descent and Markov chains, Convergence in quadratic mean of averaged stochastic gradient algorithms without strong convexity nor bounded gradient, Stochastic heavy ball, Finite-sample analysis of \(M\)-estimators using self-concordance, On variance reduction for stochastic smooth convex optimization with multiplicative noise, Unnamed Item, Unnamed Item, Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization, Unnamed Item, Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures, An Efficient Stochastic Newton Algorithm for Parameter Estimation in Logistic Regressions, A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares), Online estimation of the asymptotic variance for averaged stochastic gradient algorithms, Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression, Convergence Rate of Incremental Gradient and Incremental Newton Methods, Generalized self-concordant functions: a recipe for Newton-type methods