Image de couverture de livre

The Hessian of tall-skinny networks is easy to invert

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Rahimi, Ali
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Implementation of QR factorization of tall and very skinny matrices on current GPUs
par: Thies, Jonas, et autres
Publié: (2026)

QR factorization of ill-conditioned tall-and-skinny matrices on distributed-memory systems
par: Mijić, Nenad, et autres
Publié: (2024)

The sampling complexity of learning invertible residual neural networks
par: Li, Yuanyuan, et autres
Publié: (2024)

BayesFlow: Learning complex stochastic models with invertible neural networks
par: Radev, Stefan T., et autres
Publié: (2020)

Diffusion posterior sampling for simulation-based inference in tall data settings
par: Linhart, Julia, et autres
Publié: (2024)

The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks
par: Gabdullin, Nikita
Publié: (2025)

HessFormer: Hessians at Foundation Scale
par: Granziol, Diego
Publié: (2025)

GP-FL: Model-Based Hessian Estimation for Second-Order Over-the-Air Federated Learning
par: Hamidi, Shayan Mohajer, et autres
Publié: (2024)

AdS/Deep-Learning made easy II: neural network-based approaches to holography and inverse problems
par: Jeong, Hyun-Sik, et autres
Publié: (2025)

Hessian QM9: A quantum chemistry database of molecular Hessians in implicit solvents
par: Williams, Nicholas J., et autres
Publié: (2024)

Detecting music deepfakes is easy but actually hard
par: Afchar, Darius, et autres
Publié: (2024)

Artificial intelligence for science: The easy and hard problems
par: Battleday, Ruairidh M., et autres
Publié: (2024)

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis
par: Gabdullin, Nikita
Publié: (2024)

Scikit-fingerprints: easy and efficient computation of molecular fingerprints in Python
par: Adamczyk, Jakub, et autres
Publié: (2024)

Depth, Not Data: An Analysis of Hessian Spectral Bifurcation
par: Deng, Shenyang, et autres
Publié: (2026)

Hessian Spectral Analysis at Foundation Model Scale
par: Granziol, Diego, et autres
Publié: (2026)

Spatio-seasonal risk assessment of upward lightning at tall objects using meteorological reanalysis data
par: Stucke, Isabell, et autres
Publié: (2024)

Hessian-Informed Flow Matching
par: Sprague, Christopher Iliffe, et autres
Publié: (2024)

Semi-supervised learning with max-margin graph cuts
par: Kveton, Branislav, et autres
Publié: (2026)

Active partitioning: inverting the paradigm of active learning
par: Tacke, Marius, et autres
Publié: (2024)

Neglected Hessian component explains mysteries in Sharpness regularization
par: Dauphin, Yann N., et autres
Publié: (2024)

Revisit, Extend, and Enhance Hessian-Free Influence Functions
par: Yang, Ziao, et autres
Publié: (2024)

Bayesian Influence Functions for Hessian-Free Data Attribution
par: Kreer, Philipp Alexander, et autres
Publié: (2025)

Hessian-Free Online Certified Unlearning
par: Qiao, Xinbao, et autres
Publié: (2024)

Stochastic Hessian Fittings with Lie Groups
par: Li, Xi-Lin
Publié: (2024)

Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
par: Osada, Genki
Publié: (2026)

Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents
par: Alver, Safa, et autres
Publié: (2024)

The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank
par: Bar, Amitay, et autres
Publié: (2024)

Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization
par: Chen, Yuen, et autres
Publié: (2025)

A Hessian-informed hyperparameter optimization for differential learning rate
par: Xu, Shiyun, et autres
Publié: (2025)

Revisiting inverse Hessian vector products for calculating influence functions
par: Klochkov, Yegor, et autres
Publié: (2024)

Preference learning made easy: Everything should be understood through win rate
par: Zhang, Lily H., et autres
Publié: (2025)

Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
par: Vigna, Hugo, et autres
Publié: (2026)

An invertible generative model for forward and inverse problems
par: van Leeuwen, Tristan, et autres
Publié: (2025)

Weighted Stochastic Differential Equation to Implement Wasserstein-Fisher-Rao Gradient Flow
par: Rahimi, Herlock
Publié: (2025)

Community detection with the Bethe-Hessian
par: Stephan, Ludovic, et autres
Publié: (2024)

Gradient-Normalized Smoothness for Optimization with Approximate Hessians
par: Semenov, Andrei, et autres
Publié: (2025)

Towards Quantifying the Hessian Structure of Neural Networks
par: Dong, Zhaorui, et autres
Publié: (2025)

Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods
par: Fernandez, Andres, et autres
Publié: (2025)

Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes
par: Kiselev, Nikita, et autres
Publié: (2024)