A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training
From MaRDI portal
Publication:6055115
DOI10.1016/j.neunet.2021.05.011zbMath1521.68122arXiv2103.07554OpenAlexW3169062464MaRDI QIDQ6055115
No author found.
Publication date: 28 September 2023
Published in: Neural Networks (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2103.07554
conjugate gradientnatural gradientHessian-freediscriminative sequence trainingsecond-order optimisation
Related Items (3)
A second-order accelerated neurodynamic approach for distributed convex optimization ⋮ Guest editorial: Special issue on advances in deep learning based speech processing ⋮ An overview of stochastic quasi-Newton methods for large-scale machine learning
Cites Work
- Information geometry and its applications
- Reducing the Dimensionality of Data with Neural Networks
- Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent
- Large-Scale Machine Learning with Stochastic Gradient Descent
- Optimization Methods for Large-Scale Machine Learning
- Learning representations by back-propagating errors
- A Fast Learning Algorithm for Deep Belief Nets
- An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
This page was built for publication: A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training