Imagen de Portada

Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fernandez, Andres, Schneider, Frank, Mahsereci, Maren, Hennig, Philipp
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Bayesian Quadrature: Gaussian Processes for Integration
por: Mahsereci, Maren, et al.
Publicado: (2026)

A Dictionary of Closed-Form Kernel Mean Embeddings
por: Briol, François-Xavier, et al.
Publicado: (2025)

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

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

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

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

Scaling up Probabilistic PDE Simulators with Structured Volumetric Information
por: Weiland, Tim, et al.
Publicado: (2024)

FINDER: Feature Inference on Noisy Datasets using Eigenspace Residuals
por: Murphy, Trajan, et al.
Publicado: (2025)

Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds
por: Yang, Zherui, et al.
Publicado: (2026)

HessFormer: Hessians at Foundation Scale
por: Granziol, Diego
Publicado: (2025)

Gaussian Processes and Reproducing Kernels: Connections and Equivalences
por: Kanagawa, Motonobu, et al.
Publicado: (2025)

Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations
por: Beck, Jonas, et al.
Publicado: (2024)

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

First-ish Order Methods: Hessian-aware Scalings of Gradient Descent
por: Smee, Oscar, et al.
Publicado: (2025)

Hessian Spectral Analysis at Foundation Model Scale
por: Granziol, Diego, et al.
Publicado: (2026)

Deep Eigenspace Network for Parametric Non-self-adjoint Eigenvalue Problems
por: Li, H., et al.
Publicado: (2025)

Comparing Scale Parameter Estimators for Gaussian Process Interpolation with the Brownian Motion Prior: Leave-One-Out Cross Validation and Maximum Likelihood
por: Naslidnyk, Masha, et al.
Publicado: (2023)

Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning
por: He, JinLi, et al.
Publicado: (2026)

Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions
por: Prato, Tahmid Hasan, et al.
Publicado: (2025)

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

Latent Geometry as a Structural Monitor: Eigenspace Alignment for Anomaly Detection in Anonymity Networks
por: Chhabra, Vaibhav
Publicado: (2026)

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

Scaling Federated Linear Contextual Bandits via Sketching
por: Yang, Hantao, et al.
Publicado: (2026)

On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks
por: Redman, William T., et al.
Publicado: (2024)

Assessing the risk of future Dunkelflaute events for Germany using generative deep learning
por: Strnad, Felix, et al.
Publicado: (2025)

Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields
por: Weiland, Tim, et al.
Publicado: (2025)

Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
por: Romanov, Elad, et al.
Publicado: (2024)

Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching
por: Jiang, Shan, et al.
Publicado: (2026)

Debiasing Mini-Batch Quadratics for Applications in Deep Learning
por: Tatzel, Lukas, et al.
Publicado: (2024)

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

GaLLoP: Gradient-based Sparse Learning on Low-Magnitude Parameters
por: Choudhary, Anand, et al.
Publicado: (2025)

Wasserstein t-SNE
por: Bachmann, Fynn, et al.
Publicado: (2022)

FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds
por: Tabealhojeh, Hadi, et al.
Publicado: (2024)

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

Estimation of Motor Unit Parameters from Surface Electromyograms using an Informed Autoencoder
por: Balzereit, Kaja, et al.
Publicado: (2026)

Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
por: Zhang, Tianyi, et al.
Publicado: (2024)

Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks
por: Jin, Dian, et al.
Publicado: (2025)

SketchGuard: Scaling Byzantine-Robust Decentralized Federated Learning via Sketch-Based Screening
por: Rangwala, Murtaza, et al.
Publicado: (2025)

Computation-Aware Kalman Filtering and Smoothing
por: Pförtner, Marvin, et al.
Publicado: (2024)