No article text was recorded for this version.
Fisher Information Matrix scalability
Version 2 of 2117 papers126 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Fishy: Layerwise Fisher Approximation for Higher-order Neural Network Optimization
- Blog: New Insights and Perspectives on the Natural Gradient Method
- Blog: An Improved Empirical Fisher Approximation for Natural Gradient Descent
- Blog: An Improved Empirical Fisher Approximation for Natural Gradient Descent
- Blog: A Novel Structured Natural Gradient Descent for Deep Learning
- Blog: A Reparametrization-Invariant Sharpness Measure Based on Information Geometry
- Blog: Tractable structured natural gradient descent using local parameterizations
- Blog: On the Computation of the Fisher Information in Continual Learning
- Blog: Riemannian Laplace Approximation with the Fisher Metric
- Blog: Continual Learning in Deep Neural Network by Using a Kalman Optimiser
- Blog: Fisher Information and Natural Gradient Learning in Random Deep Networks
- Blog: Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models
- Blog: FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity
- Blog: The Implicit Delta Method
- Blog: Compatible natural gradient policy search
- Blog: Repairing Neural Networks by Leaving the Right Past Behind
- Blog: Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
- Blog: Measuring Stochastic Data Complexity with Boltzmann Influence Functions
- Blog: Black-box Optimizer with Implicit Natural Gradient
- Blog: Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations
- Blog: Convolutional Neural Network Training with Distributed K-FAC
- Blog: Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
- Blog: Effective dimension of machine learning models
- Blog: Scalable Kronecker-Factored Fisher Approximation for Neural Network Parameter Sensitivity
- Blog: RRL: Recommendation Reverse Learning
- Blog: Information Splitting for Big Data Analytics
- Blog: An Improved Empirical Fisher Approximation for Natural Gradient Descent
- Blog: Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation
- Blog: A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
- Blog: Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach
- Blog: Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
- Blog: Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis
- Blog: Geometry matters: Exploring language examples at the decision boundary
- Blog: High dimensional optimal design using stochastic gradient optimisation and Fisher information gain
- Blog: Relative Fisher Information and Natural Gradient for Learning Large Modular Models
- Blog: Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning
- Blog: An Evaluation of Fisher Approximations Beyond Kronecker Factorization
- Blog: Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines
- Blog: Eigenvalue-corrected Natural Gradient Based on a New Approximation
- Blog: Detection of Review Abuse via Semi-Supervised Binary Multi-Target Tensor Decomposition
- Blog: Tensor Normal Training for Deep Learning Models
- Blog: Tractable structured natural-gradient descent using local parameterizations
- Blog: Optimization of Graph Neural Networks with Natural Gradient Descent
- Blog: Information-Theoretic Local Minima Characterization and Regularization
- Blog: Limitations of the empirical Fisher approximation for natural gradient descent
- Blog: AIMS: Average information matrix splitting
- Blog: Stochastic Variance Reduction for Policy Gradient Estimation
- Blog: Towards Modeling and Resolving Singular Parameter Spaces using Stratifolds
- Blog: Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Models
- Blog: Natural evolution strategies and quantum approximate optimization
- Blog: AdaBlock: SGD with Practical Block Diagonal Matrix Adaptation for Deep Learning
- Blog: LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
- Blog: Efficient Natural Evolution Strategies
- Blog: Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
- Blog: NPEFF: Non-Negative Per-Example Fisher Factorization
- Blog: Geometry matters: Exploring language examples at the decision boundary
- Blog: Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
- Blog: Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights
- Blog: Understanding Deep Learning by Revisiting Boltzmann Machines: An Information Geometry Approach
- Blog: Bayesian polynomial neural networks and polynomial neural ordinary differential equations
Showing 60 of 117 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_fisher_information_matrix_scalability_0b052e11,
title = {Fisher Information Matrix scalability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/fisher-information-matrix-scalability/rdr_0b052e11cbbf4963838266229434516b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_fisher_information_matrix_scalability_0b052e11_v2,
title = {Fisher Information Matrix scalability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/fisher-information-matrix-scalability/rdr_0b052e11cbbf4963838266229434516b/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}