Cover Image

The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Gabdullin, Nikita
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces
by: Gabdullin, Nikita
Published: (2025)

Using predefined vector systems to speed up neural network multimillion class classification
by: Gabdullin, Nikita, et al.
Published: (2026)

Using predefined vector systems as latent space configuration for neural network supervised training on data with arbitrarily large number of classes
by: Gabdullin, Nikita
Published: (2025)

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

Latent space configuration for improved generalization in supervised autoencoder neural networks
by: Gabdullin, Nikita
Published: (2024)

Visualizing high-dimensional loss landscapes with Hessian directions
by: Böttcher, Lucas, et al.
Published: (2022)

Improving analytical color and texture similarity estimation methods for dataset-agnostic person reidentification
by: Gabdullin, Nikita
Published: (2024)

EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
by: Gordon, Ofir, et al.
Published: (2023)

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
by: Wang, Zhong, et al.
Published: (2026)

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
by: He, Yuhao, et al.
Published: (2024)

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
by: Wang, YiFeng, et al.
Published: (2026)

CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems
by: Uddin, Mohammad Helal, et al.
Published: (2025)

On margin-based generalization prediction in deep neural networks
by: Mouton, Coenraad
Published: (2024)

Multi-task convolutional neural network for image aesthetic assessment
by: Soydaner, Derya, et al.
Published: (2023)

FAWN: Floor-And-Walls Normal Regularization for Direct Neural TSDF Reconstruction
by: Sokolova, Anna, et al.
Published: (2024)

Hessian Geometry of Latent Space in Generative Models
by: Lobashev, Alexander, et al.
Published: (2025)

Mapping Rio de Janeiro's favelas: general-purpose vs. satellite-specific neural networks
by: Hallopeau, Thomas, et al.
Published: (2025)

Aligned explanations in neural networks
by: Lobet, Corentin, et al.
Published: (2026)

Equivariant neural networks and equivarification
by: Bao, Erkao, et al.
Published: (2019)

On the explainability of max-plus neural networks
by: Enaieh, Ikhlas, et al.
Published: (2026)

Are classical deep neural networks weakly adversarially robust?
by: Sun, Nuolin, et al.
Published: (2025)

Characterization of topological structures in different neural network architectures
by: Świder, Paweł
Published: (2024)

Kinematic analysis of structural mechanics based on convolutional neural network
by: Zhang, Leye, et al.
Published: (2024)

Sparse components distinguish visual pathways & their alignment to neural networks
by: Marvi, Ammar I, et al.
Published: (2025)

Spectral structural distortion reveals redundant neurons in neural networks
by: Wang, Yongyu
Published: (2026)

Neural network relief: a pruning algorithm based on neural activity
by: Dekhovich, Aleksandr, et al.
Published: (2021)

Training morphological neural networks with gradient descent: some theoretical insights
by: Blusseau, Samy
Published: (2024)

Exploring Kolmogorov-Arnold networks for realistic image sharpness assessment
by: Yu, Shaode, et al.
Published: (2024)

Graph neural network for colliding particles with an application to sea ice floe modeling
by: Zhu, Ruibiao
Published: (2026)

Reduced storage direct tensor ring decomposition for convolutional neural networks compression
by: Gabor, Mateusz, et al.
Published: (2024)

InfoGNN: End-to-end deep learning on mesh via graph neural networks
by: Gao, Ling, et al.
Published: (2025)

Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratch
by: Badar, Zia
Published: (2025)

Real-time prediction of breast cancer sites using deformation-aware graph neural network
by: Lee, Kyunghyun, et al.
Published: (2025)

GD doesn't make the cut: Three ways that non-differentiability affects neural network training
by: Kumar, Siddharth Krishna
Published: (2024)

Hand bone age estimation using divide and conquer strategy and lightweight convolutional neural networks
by: Kasani, Amin Ahmadi, et al.
Published: (2024)

A two-stream network with global-local feature fusion for bone age assessment
by: Lou, Qiong, et al.
Published: (2025)

Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
by: Perera, Maneesha, et al.
Published: (2024)

An approach based on class activation maps for investigating the effects of data augmentation on neural networks for image classification
by: Dorneles, Lucas M., et al.
Published: (2025)

Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix
by: Pang, Junbiao, et al.
Published: (2025)