:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Hong, Steve, Eschenhagen, Runa, Mlodozeniec, Bruno, Turner, Richard
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	https://arxiv.org/abs/2509.23437
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
por: Eschenhagen, Runa, et al.
Publicado: (2023)

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

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

Probabilistic Modelling is Sufficient for Causal Inference
por: Mlodozeniec, Bruno, et al.
Publicado: (2025)

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

Distributional Training Data Attribution: What do Influence Functions Sample?
por: Mlodozeniec, Bruno, 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)

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

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

Incremental Transformer Neural Processes
por: Mortimer, Philip, et al.
Publicado: (2026)

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

Denoising Diffusion Probabilistic Models in Six Simple Steps
por: Turner, Richard E., et al.
Publicado: (2024)

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

Bayesian Influence Functions for Hessian-Free Data Attribution
por: Kreer, Philipp Alexander, et al.
Publicado: (2025)

Revisit, Extend, and Enhance Hessian-Free Influence Functions
por: Yang, Ziao, et al.
Publicado: (2024)

A Generative Model of Symmetry Transformations
por: Allingham, James Urquhart, et al.
Publicado: (2024)

Warm Start Marginal Likelihood Optimisation for Iterative Gaussian Processes
por: Lin, Jihao Andreas, et al.
Publicado: (2024)

Better Training Data Attribution via Better Inverse Hessian-Vector Products
por: Wang, Andrew, et al.
Publicado: (2025)

Implicit meta-learning may lead language models to trust more reliable sources
por: Krasheninnikov, Dmitrii, et al.
Publicado: (2023)

Rotary Position Encodings for Graphs
por: Reid, Isaac, et al.
Publicado: (2025)

Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens
por: Qiu, Junbin, et al.
Publicado: (2026)

Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
por: Lin, Jihao Andreas, et al.
Publicado: (2024)

Gradient-Normalized Smoothness for Optimization with Approximate Hessians
por: Semenov, Andrei, et al.
Publicado: (2025)

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
por: Mlodozeniec, Bruno, et al.
Publicado: (2025)

FAGH: Accelerating Federated Learning with Approximated Global Hessian
por: Sen, Mrinmay, et al.
Publicado: (2024)

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

Subspace-based Approximate Hessian Method for Zeroth-Order Optimization
por: Kim, Dongyoon, et al.
Publicado: (2025)

Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
por: Elsayed, Mohamed, et al.
Publicado: (2024)

Projected Hessian Learning: Fast Curvature Supervision for Accurate Machine-Learning Interatomic Potentials
por: Rodriguez, Austin, et al.
Publicado: (2026)

Closing the Curvature Gap: Full Transformer Hessians and Their Implications for Scaling Laws
por: Petrov, Egor, et al.
Publicado: (2025)

Mimicking Better by Matching the Approximate Action Distribution
por: Ramos, João A. Cândido, et al.
Publicado: (2023)

SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation
por: Shin, Dahun, et al.
Publicado: (2025)

The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models
por: Lev, Omri, et al.
Publicado: (2024)

Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes
por: Kiselev, Nikita, et al.
Publicado: (2024)

Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization
por: Dong, Youran, et al.
Publicado: (2025)

Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms
por: Godichon-Baggioni, Antoine, et al.
Publicado: (2024)

MAC: An Efficient Gradient Preconditioning using Mean Activation Approximated Curvature
por: Seung, Hyunseok, et al.
Publicado: (2025)

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

Unbiased Online Curvature Approximation for Regularized Graph Continual Learning
por: Yin, Jie, et al.
Publicado: (2025)