Copertina

The Hessian of tall-skinny networks is easy to invert

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Rahimi, Ali
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Implementation of QR factorization of tall and very skinny matrices on current GPUs
di: Thies, Jonas, et al.
Pubblicazione: (2026)

QR factorization of ill-conditioned tall-and-skinny matrices on distributed-memory systems
di: Mijić, Nenad, et al.
Pubblicazione: (2024)

The sampling complexity of learning invertible residual neural networks
di: Li, Yuanyuan, et al.
Pubblicazione: (2024)

BayesFlow: Learning complex stochastic models with invertible neural networks
di: Radev, Stefan T., et al.
Pubblicazione: (2020)

Diffusion posterior sampling for simulation-based inference in tall data settings
di: Linhart, Julia, et al.
Pubblicazione: (2024)

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

HessFormer: Hessians at Foundation Scale
di: Granziol, Diego
Pubblicazione: (2025)

GP-FL: Model-Based Hessian Estimation for Second-Order Over-the-Air Federated Learning
di: Hamidi, Shayan Mohajer, et al.
Pubblicazione: (2024)

AdS/Deep-Learning made easy II: neural network-based approaches to holography and inverse problems
di: Jeong, Hyun-Sik, et al.
Pubblicazione: (2025)

Hessian QM9: A quantum chemistry database of molecular Hessians in implicit solvents
di: Williams, Nicholas J., et al.
Pubblicazione: (2024)

Detecting music deepfakes is easy but actually hard
di: Afchar, Darius, et al.
Pubblicazione: (2024)

Artificial intelligence for science: The easy and hard problems
di: Battleday, Ruairidh M., et al.
Pubblicazione: (2024)

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

Scikit-fingerprints: easy and efficient computation of molecular fingerprints in Python
di: Adamczyk, Jakub, et al.
Pubblicazione: (2024)

Depth, Not Data: An Analysis of Hessian Spectral Bifurcation
di: Deng, Shenyang, et al.
Pubblicazione: (2026)

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

Spatio-seasonal risk assessment of upward lightning at tall objects using meteorological reanalysis data
di: Stucke, Isabell, et al.
Pubblicazione: (2024)

Hessian-Informed Flow Matching
di: Sprague, Christopher Iliffe, et al.
Pubblicazione: (2024)

Semi-supervised learning with max-margin graph cuts
di: Kveton, Branislav, et al.
Pubblicazione: (2026)

Active partitioning: inverting the paradigm of active learning
di: Tacke, Marius, et al.
Pubblicazione: (2024)

Neglected Hessian component explains mysteries in Sharpness regularization
di: Dauphin, Yann N., et al.
Pubblicazione: (2024)

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

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

Hessian-Free Online Certified Unlearning
di: Qiao, Xinbao, et al.
Pubblicazione: (2024)

Stochastic Hessian Fittings with Lie Groups
di: Li, Xi-Lin
Pubblicazione: (2024)

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

Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents
di: Alver, Safa, et al.
Pubblicazione: (2024)

The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank
di: Bar, Amitay, et al.
Pubblicazione: (2024)

Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization
di: Chen, Yuen, et al.
Pubblicazione: (2025)

A Hessian-informed hyperparameter optimization for differential learning rate
di: Xu, Shiyun, et al.
Pubblicazione: (2025)

Revisiting inverse Hessian vector products for calculating influence functions
di: Klochkov, Yegor, et al.
Pubblicazione: (2024)

Preference learning made easy: Everything should be understood through win rate
di: Zhang, Lily H., et al.
Pubblicazione: (2025)

Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
di: Vigna, Hugo, et al.
Pubblicazione: (2026)

An invertible generative model for forward and inverse problems
di: van Leeuwen, Tristan, et al.
Pubblicazione: (2025)

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

Community detection with the Bethe-Hessian
di: Stephan, Ludovic, et al.
Pubblicazione: (2024)

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

Towards Quantifying the Hessian Structure of Neural Networks
di: Dong, Zhaorui, et al.
Pubblicazione: (2025)

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

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