Pages that link to "Item:Q3150014"
From MaRDI portal
The following pages link to Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent (Q3150014):
Displaying 23 items.
- A survey on learning approaches for undirected graphical models. Application to scene object recognition (Q518649) (← links)
- A stochastic conjugate gradient method for the approximation of functions (Q765306) (← links)
- A survey on deep learning and its applications (Q826338) (← links)
- Optimization for deep learning: an overview (Q2218095) (← links)
- Speeding up the scaled conjugate gradient algorithm and its application in neuro-fuzzy classifier training (Q2380342) (← links)
- Efficient Calculation of the Gauss-Newton Approximation of the Hessian Matrix in Neural Networks (Q2885106) (← links)
- Limited Stochastic Meta-Descent for Kernel-Based Online Learning (Q3182496) (← links)
- Accelerated Methods for NonConvex Optimization (Q4571877) (← links)
- A matrix-free line-search algorithm for nonconvex optimization (Q4646671) (← links)
- First-Order Methods for Nonconvex Quadratic Minimization (Q5113167) (← links)
- (Q5148924) (← links)
- Distributed Newton Methods for Deep Neural Networks (Q5157199) (← links)
- Gradient Descent Finds the Cubic-Regularized Nonconvex Newton Step (Q5233102) (← links)
- Subsampled Hessian Newton Methods for Supervised Learning (Q5380307) (← links)
- SCORE: approximating curvature information under self-concordant regularization (Q6051307) (← links)
- A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training (Q6055115) (← links)
- An overview of stochastic quasi-Newton methods for large-scale machine learning (Q6097379) (← links)
- Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems (Q6116387) (← links)
- A \(J\)-symmetric quasi-Newton method for minimax problems (Q6120841) (← links)
- Efficient approximations of the fisher matrix in neural networks using kronecker product singular value decomposition (Q6127062) (← links)
- Riemannian Natural Gradient Methods (Q6189169) (← links)
- Enhancing training of physics-informed neural networks using domain decomposition-based preconditioning strategies (Q6623675) (← links)
- Visualizing high-dimensional loss landscapes with Hessian directions (Q6625316) (← links)
