Image de couverture de livre

Visualizing high-dimensional loss landscapes with Hessian directions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Böttcher, Lucas, Wheeler, Gregory
Format:	Preprint
Publié:	2022
Sujets:	Machine Learning Computer Vision and Pattern Recognition Computation
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

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

Visualizing the loss landscape of Self-supervised Vision Transformer
par: Lee, Youngwan, et autres
Publié: (2024)

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
par: Wang, Zhong, et autres
Publié: (2026)

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

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)

EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
par: Gordon, Ofir, et autres
Publié: (2023)

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
par: Wang, YiFeng, et autres
Publié: (2026)

Object-Centric Cropping for Visual Few-Shot Classification
par: Abdali, Aymane, et autres
Publié: (2025)

CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems
par: Uddin, Mohammad Helal, et autres
Publié: (2025)

Parallel Backpropagation for Shared-Feature Visualization
par: Lappe, Alexander, et autres
Publié: (2024)

National level satellite-based crop field inventories in smallholder landscapes
par: Rufin, Philippe, et autres
Publié: (2025)

A margin-based replacement for cross-entropy loss
par: Spratling, Michael W., et autres
Publié: (2025)

Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
par: Bellchambers, Gregory
Publié: (2025)

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
par: He, Yuhao, et autres
Publié: (2024)

FogGuard: guarding YOLO against fog using perceptual loss
par: Gharatappeh, Soheil, et autres
Publié: (2024)

A hierarchical loss and its problems when classifying non-hierarchically
par: Wu, Cinna, et autres
Publié: (2017)

Inverse problems with diffusion models: MAP estimation via mode-seeking loss
par: Gutha, Sai Bharath Chandra, et autres
Publié: (2025)

Regularizing cross entropy loss via minimum entropy and K-L divergence
par: Ibraheem, Abdulrahman Oladipupo
Publié: (2025)

BMIP: Bi-directional Modality Interaction Prompt Learning for VLM
par: Lv, Song-Lin, et autres
Publié: (2025)

Bayesian generative models can flag performance loss, bias, and out-of-distribution image content
par: López-Pérez, Miguel, et autres
Publié: (2025)

Reduced storage direct tensor ring decomposition for convolutional neural networks compression
par: Gabor, Mateusz, et autres
Publié: (2024)

Visual Language Hypothesis
par: Li, Xiu
Publié: (2025)

Pretrained Visual Uncertainties
par: Kirchhof, Michael, et autres
Publié: (2024)

Multimodal Reference Visual Grounding
par: Lu, Yangxiao, et autres
Publié: (2025)

Visualize and Paint GAN Activations
par: Herdt, Rudolf, et autres
Publié: (2024)

Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing
par: Shu, Yan, et autres
Publié: (2024)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
par: Lingle, Lucas D.
Publié: (2023)

Evaluation of Audio-Visual Alignments in Visually Grounded Speech Models
par: Khorrami, Khazar, et autres
Publié: (2021)

Lecture Video Visual Objects (LVVO) Dataset: A Benchmark for Visual Object Detection in Educational Videos
par: Biswas, Dipayan, et autres
Publié: (2025)

Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models
par: Wang, Jeffrey, et autres
Publié: (2026)

Adaptive Discriminative Regularization for Visual Classification
par: Zhao, Qingsong, et autres
Publié: (2022)

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models
par: Hou, Haowen, et autres
Publié: (2024)

LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions
par: Han, Songhao, et autres
Publié: (2023)

Visually Prompted Benchmarks Are Surprisingly Fragile
par: Feng, Haiwen, et autres
Publié: (2025)

Probing Visual Language Priors in VLMs
par: Luo, Tiange, et autres
Publié: (2024)

Learning Privacy from Visual Entities
par: Xompero, Alessio, et autres
Publié: (2025)

CATVis: Context-Aware Thought Visualization
par: Mehmood, Tariq, et autres
Publié: (2025)

Learning Visual-Semantic Subspace Representations
par: Moreira, Gabriel, et autres
Publié: (2024)

Questioning the Stability of Visual Question Answering
par: Rosenfeld, Amir, et autres
Publié: (2025)

Test-Time Visual In-Context Tuning
par: Xie, Jiahao, et autres
Publié: (2025)