A New Likelihood Ratio Method for Training Artificial Neural Networks
From MaRDI portal
Publication:5084674
Recommendations
- Numerical Analysis for Convergence of a Sample-Wise Backpropagation Method for Training Stochastic Neural Networks
- Substantiation of the backpropagation technique via the Hamilton-Pontryagin formalism for training nonconvex nonsmooth neural networks
- scientific article; zbMATH DE number 1424367
- Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms
- Stochastic generalized gradient methods for training nonconvex nonsmooth neural networks
Cites work
- A measure-valued differentiation approach to sensitivities of quantiles
- A new stochastic derivative estimator for discontinuous payoff functions with application to financial derivatives
- A new unbiased stochastic derivative estimator for discontinuous sample performances with structural parameters
- A stochastic quasi-Newton method for large-scale optimization
- A Unified View of the IPA, SF, and LR Gradient Estimation Techniques
- Conditional Monte Carlo estimation of quantile sensitivities
- Convergence Properties of Infinitesimal Perturbation Analysis Estimates
- Deep learning
- DYNAMICAL, SYMPLECTIC AND STOCHASTIC PERSPECTIVES ON GRADIENT-BASED OPTIMIZATION
- Estimating quantile sensitivities
- scientific article; zbMATH DE number 439951 (Why is no real title available?)
- scientific article; zbMATH DE number 51708 (Why is no real title available?)
- scientific article; zbMATH DE number 1005357 (Why is no real title available?)
- scientific article; zbMATH DE number 1179315 (Why is no real title available?)
- Infinitesimal and finite perturbation analysis for queueing networks
- Kernel estimation of the Greeks for options with discontinuous payoffs
- Learning representations by back-propagating errors
- Managerial Applications of Neural Networks: The Case of Bank Failure Predictions
- Monte Carlo gradient estimation in machine learning
- Neural networks for modelling and control of dynamic systems. A practitioner's handbook
- On the variance of single-run unbiased stochastic derivative estimators
- Random gradient-free minimization of convex functions
- Sensitivity Analysis for Simulations via Likelihood Ratios
- Sensitivity analysis of discrete event systems by the push out method
- The score function approach for sensitivity analysis of computer simulation models
- Weak Differentiability of Product Measures
Cited in
(5)- Likelihood ratio of unidentifiable models and multilayer neural networks
- scientific article; zbMATH DE number 5898589 (Why is no real title available?)
- scientific article; zbMATH DE number 1874294 (Why is no real title available?)
- Review of large-scale simulation optimization
- Fifty years of stochastic simulation: where we are and where we need to go
This page was built for publication: A New Likelihood Ratio Method for Training Artificial Neural Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5084674)
