Skip to content
Universidad del Mar SIBUMAR Descubridor Institucional UMAR
  • Inicio
  • Búsqueda avanzada
  • Explorar
  • Login
    • English
    • Deutsch
    • Español
    • Français
    • Italiano
Advanced
  • Visualizing high-dimensional loss landscapes with Hessian directions
Cover Image

Visualizing high-dimensional loss landscapes with Hessian directions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Böttcher, Lucas, Wheeler, Gregory
Format: Preprint
Published: 2022
Subjects:
Machine Learning
Computer Vision and Pattern Recognition
Computation
Online Access:
Acceder al recurso
Tags: Add Tag
No Tags, Be the first to tag this record!
  • Cite this
  • Text this
  • Email this
  • Print
  • Export Record
    • Export to RefWorks
    • Export to EndNoteWeb
    • Export to EndNote
  • Save to List
  • Permanent link
  • Holdings
  • Description
  • Comments
  • Similar Items
  • Staff View

Internet

https://arxiv.org/abs/2208.13219

Similar Items

  • Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis
    by: Gabdullin, Nikita
    Published: (2024)
  • Visualizing the loss landscape of Self-supervised Vision Transformer
    by: Lee, Youngwan, et al.
    Published: (2024)
  • MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
    by: Wang, Zhong, et al.
    Published: (2026)
  • Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
    by: Vigna, Hugo, et al.
    Published: (2026)
  • The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks
    by: Gabdullin, Nikita
    Published: (2025)
Universidad del Mar
Universidad del MarSistema Bibliotecario de la Universidad del MarDescubridor Institucional UMARImplementación y desarrollo: Mtro. Carlos Alonso Albores Pérez
InicioBúsqueda avanzadaExplorar
Visitas al Descubridor: 276,804© 2026 Universidad del Mar