The following pages link to (Q5148924):
Displaying 35 items.
- Variational Bayes on manifolds (Q2058893) (← links)
- The recursive variational Gaussian approximation (R-VGA) (Q2066753) (← links)
- Parametrisation independence of the natural gradient in overparametrised systems (Q2117935) (← links)
- Information geometry of physics-informed statistical manifolds and its use in data assimilation (Q2162022) (← links)
- Sketch-based empirical natural gradient methods for deep learning (Q2162326) (← links)
- Laplace approximation and natural gradient for Gaussian process regression with heteroscedastic Student-\(t\) model (Q2329797) (← links)
- Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions (Q2693789) (← links)
- Optimization Methods for Large-Scale Machine Learning (Q4641709) (← links)
- Warped Riemannian Metrics for Location-Scale Models (Q4967761) (← links)
- (Q4998868) (← links)
- Structure-preserving deep learning (Q5014474) (← links)
- Understanding approximate Fisher information for fast convergence of natural gradient descent in wide neural networks* (Q5020052) (← links)
- A fully stochastic second-order trust region method (Q5043844) (← links)
- QNG: A Quasi-Natural Gradient Method for Large-Scale Statistical Learning (Q5067429) (← links)
- Model-Centric Data Manifold: The Data Through the Eyes of the Model (Q5094635) (← links)
- Stochastic sub-sampled Newton method with variance reduction (Q5204645) (← links)
- A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training (Q6055115) (← links)
- Epistemic uncertainty quantification in deep learning classification by the delta method (Q6055168) (← links)
- Approximate Newton Policy Gradient Algorithms (Q6074547) (← links)
- Semi-implicit back propagation (Q6085636) (← links)
- Robust federated learning under statistical heterogeneity via hessian-weighted aggregation (Q6097164) (← links)
- An overview of stochastic quasi-Newton methods for large-scale machine learning (Q6097379) (← links)
- On the locality of the natural gradient for learning in deep Bayesian networks (Q6115102) (← links)
- Invariance properties of the natural gradient in overparametrised systems (Q6115103) (← links)
- Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems (Q6116387) (← links)
- Geometry and convergence of natural policy gradient methods (Q6138809) (← links)
- Deep learning and geometric deep learning: An introduction for mathematicians and physicists (Q6144784) (← links)
- Multi-agent natural actor-critic reinforcement learning algorithms (Q6159507) (← links)
- The limited-memory recursive variational Gaussian approximation (L-RVGA) (Q6172928) (← links)
- Riemannian Natural Gradient Methods (Q6189169) (← links)
- Natural reweighted wake-sleep (Q6488734) (← links)
- Sufficient dimension reduction for a novel class of zero-inflated graphical models (Q6573301) (← links)
- Convergence of entropy-regularized natural policy gradient with linear function approximation (Q6587339) (← links)
- Visualizing high-dimensional loss landscapes with Hessian directions (Q6625316) (← links)
- Natural gradient hybrid variational inference with application to deep mixed models (Q6643219) (← links)
