Imagen de Portada

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Eschenhagen, Runa, Immer, Alexander, Turner, Richard E., Schneider, Frank, Hennig, Philipp
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Kronecker-factored Approximate Curvature (KFAC) From Scratch
por: Dangel, Felix, et al.
Publicado: (2025)

Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions
por: Hong, Steve, et al.
Publicado: (2025)

Influence Functions for Scalable Data Attribution in Diffusion Models
por: Mlodozeniec, Bruno, et al.
Publicado: (2024)

Spectral-factorized Positive-definite Curvature Learning for NN Training
por: Lin, Wu, et al.
Publicado: (2025)

Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
por: Dangel, Felix, et al.
Publicado: (2024)

Position: Curvature Matrices Should Be Democratized via Linear Operators
por: Dangel, Felix, et al.
Publicado: (2025)

Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition
por: Kasimbeg, Priya, et al.
Publicado: (2025)

Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
por: Lin, Wu, et al.
Publicado: (2024)

Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC
por: Lin, Wu, et al.
Publicado: (2023)

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner
por: Eschenhagen, Runa, et al.
Publicado: (2025)

A New Way: Kronecker-Factored Approximate Curvature Deep Hedging and its Benefits
por: Enkhbayar, Tsogt-Ochir
Publicado: (2024)

Benchmarking Neural Network Training Algorithms
por: Dahl, George E., et al.
Publicado: (2023)

Accelerating Non-Conjugate Gaussian Processes By Trading Off Computation For Uncertainty
por: Tatzel, Lukas, et al.
Publicado: (2023)

Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods
por: Fernandez, Andres, et al.
Publicado: (2025)

Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood
por: Dhahri, Rayen, et al.
Publicado: (2024)

Rethinking Approximate Gaussian Inference in Classification
por: Mucsányi, Bálint, et al.
Publicado: (2025)

Approximately Equivariant Neural Processes
por: Ashman, Matthew, et al.
Publicado: (2024)

Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory
por: Eschenhagen, Runa, et al.
Publicado: (2026)

Sketching Low-Rank Plus Diagonal Matrices
por: Fernandez, Andres, et al.
Publicado: (2025)

Weaver: Kronecker Product Approximations of Spatiotemporal Attention for Traffic Network Forecasting
por: Cheong, Christopher, et al.
Publicado: (2025)

Improving Neural Additive Models with Bayesian Principles
por: Bouchiat, Kouroche, et al.
Publicado: (2023)

Low-Rank Filtering and Smoothing for Sequential Deep Learning
por: Sliwa, Joanna, et al.
Publicado: (2024)

Mitigating Forgetting in Low Rank Adaptation
por: Sliwa, Joanna, et al.
Publicado: (2025)

Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization
por: Lin, Wu, et al.
Publicado: (2025)

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions
por: Schmidt, Jonathan, et al.
Publicado: (2023)

Geometric Gaussian Approximations of Probability Distributions
por: Da Costa, Nathaël, et al.
Publicado: (2025)

KFCPO: Kronecker-Factored Approximated Constrained Policy Optimization
por: Lim, Joonyoung, et al.
Publicado: (2025)

Rethinking Bregman Divergences in Kronecker-Factored Optimizers
por: Liu, Bing, et al.
Publicado: (2026)

Spatio-Temporal Graph Convolutional Networks: Optimised Temporal Architecture
por: Turner, Edward
Publicado: (2025)

Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks
por: Hao, Yongchang, et al.
Publicado: (2024)

Analysis and Approximate Inference of Large Random Kronecker Graphs
por: Liao, Zhenyu, et al.
Publicado: (2023)

Generalized Fisher-Weighted SVD: Scalable Kronecker-Factored Fisher Approximation for Compressing Large Language Models
por: Chekalina, Viktoriia, et al.
Publicado: (2025)

Deep Kronecker Network
por: Feng, Long, et al.
Publicado: (2022)

FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
por: Cinquin, Tristan, et al.
Publicado: (2024)

Scalable Bayesian Inference for Nonlinear Conservation Laws
por: Weiland, Tim, et al.
Publicado: (2026)

laplax -- Laplace Approximations with JAX
por: Weber, Tobias, et al.
Publicado: (2025)

Analyzing Neural Network Robustness Using Graph Curvature
por: Tan, Shuhang, et al.
Publicado: (2024)

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
por: Kurochkin, Vadim, et al.
Publicado: (2025)

Uncertainty-Penalized Direct Preference Optimization
por: Houliston, Sam, et al.
Publicado: (2024)

Topology of Out-of-Distribution Examples in Deep Neural Networks
por: Datta, Esha, et al.
Publicado: (2025)