Complexity reduction in online stochastic Newton methods with potential O(Nd) total cost
From MaRDI portal
Publication:7347672
Cites work
- Acceleration of Stochastic Approximation by Averaging
- Adaptive subgradient methods for online learning and stochastic optimization
- An efficient averaged stochastic Gauss-Newton algorithm for estimating parameters of nonlinear regressions models
- An efficient stochastic Newton algorithm for parameter estimation in logistic regressions
- Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms
- Asymptotic and finite-sample properties of estimators based on stochastic gradients
- New method of stochastic approximation type
- Non-asymptotic analysis of Stochastic approximation algorithms for streaming data
- On adaptive stochastic optimization for streaming data: a Newton's method with \( \mathcal{O}(dN)\) operations
- On the almost sure asymptotic behaviour of stochastic algorithm
- On the asymptotic rate of convergence of stochastic Newton algorithms and their weighted averaged versions
- On the use of stochastic Hessian information in optimization methods for machine learning
- Online estimation of the asymptotic variance for averaged stochastic gradient algorithms
- Optimization methods for large-scale machine learning
- Quasi-Newton Methods, Motivation and Theory
- Randomized quasi-Newton updates are linearly convergent matrix inversion algorithms
- Second-order stochastic optimization for machine learning in linear time
- Stochastic algorithms
- Stochastic multi-stage optimization. At the crossroads between discrete time stochastic control and stochastic programming
- Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
This page was built for publication: Complexity reduction in online stochastic Newton methods with potential \(\mathcal{O}(Nd)\) total cost
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7347672)
