Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent
From MaRDI portal
Publication:3150014
DOI10.1162/08997660260028683zbMath1037.68119OpenAlexW2130984546WikidataQ52038024 ScholiaQ52038024MaRDI QIDQ3150014
Publication date: 2002
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/08997660260028683
Related Items (21)
Efficient Calculation of the Gauss-Newton Approximation of the Hessian Matrix in Neural Networks ⋮ A survey on deep learning and its applications ⋮ Speeding up the scaled conjugate gradient algorithm and its application in neuro-fuzzy classifier training ⋮ Limited Stochastic Meta-Descent for Kernel-Based Online Learning ⋮ Accelerated Methods for NonConvex Optimization ⋮ SCORE: approximating curvature information under self-concordant regularization ⋮ A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training ⋮ An overview of stochastic quasi-Newton methods for large-scale machine learning ⋮ Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems ⋮ A \(J\)-symmetric quasi-Newton method for minimax problems ⋮ Efficient approximations of the fisher matrix in neural networks using kronecker product singular value decomposition ⋮ First-Order Methods for Nonconvex Quadratic Minimization ⋮ Riemannian Natural Gradient Methods ⋮ Subsampled Hessian Newton Methods for Supervised Learning ⋮ Optimization for deep learning: an overview ⋮ Distributed Newton Methods for Deep Neural Networks ⋮ A matrix-free line-search algorithm for nonconvex optimization ⋮ A survey on learning approaches for undirected graphical models. Application to scene object recognition ⋮ Gradient Descent Finds the Cubic-Regularized Nonconvex Newton Step ⋮ A stochastic conjugate gradient method for the approximation of functions ⋮ Unnamed Item
Cites Work
This page was built for publication: Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent
