Image de couverture de livre

Sharp Minima Can Generalize: A Loss Landscape Perspective On Data

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fan, Raymond, Sandlund, Bryce, Ko, Lin Myat
Format:	Preprint
Publié:	2025
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

A Function-Centric Perspective on Flat and Sharp Minima
par: Mason-Williams, Israel, et autres
Publié: (2025)

Sharpness of Minima in Deep Matrix Factorization
par: Kamber, Anil, et autres
Publié: (2025)

Bilateral Sharpness-Aware Minimization for Flatter Minima
par: Deng, Jiaxin, et autres
Publié: (2024)

On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness
par: Kamber, Anil, et autres
Publié: (2026)

Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
par: Zhou, Zhanpeng, et autres
Publié: (2024)

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
par: Chen, Huanran, et autres
Publié: (2026)

Model Merging on Loss Landscape: A Geometry Perspective
par: Lu, Juanwu, et autres
Publié: (2026)

Challenges in Training PINNs: A Loss Landscape Perspective
par: Rathore, Pratik, et autres
Publié: (2024)

Evaluating Loss Landscapes from a Topology Perspective
par: Xie, Tiankai, et autres
Publié: (2024)

Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
par: Fang, Kun, et autres
Publié: (2023)

A Flat Minima Perspective on Understanding Augmentations and Model Robustness
par: Yoo, Weebum, et autres
Publié: (2025)

Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization
par: Wu, Wenhan, et autres
Publié: (2025)

Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics
par: Jacobsen, Albert Kjøller, et autres
Publié: (2026)

Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
par: Schioppa, Andrea
Publié: (2024)

Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
par: Jeon, Dongjae, et autres
Publié: (2024)

Sensitivity Analysis On Loss Landscape
par: Faroz, Salman
Publié: (2024)

Nonnegative Low-rank Matrix Recovery Can Have Spurious Local Minima
par: Zhang, Richard Y.
Publié: (2025)

Flat Minima and Generalization: Insights from Stochastic Convex Optimization
par: Schliserman, Matan, et autres
Publié: (2025)

Bringing the Discussion of Minima Sharpness to the Audio Domain: a Filter-Normalised Evaluation for Acoustic Scene Classification
par: Milling, Manuel, et autres
Publié: (2023)

Neural Network Plasticity and Loss Sharpness
par: Koster, Max, et autres
Publié: (2024)

Are Flat Minima an Illusion?
par: Bennett, Michael Timothy
Publié: (2026)

LSAM: Asynchronous Distributed Training with Landscape-Smoothed Sharpness-Aware Minimization
par: Teng, Yunfei, et autres
Publié: (2025)

Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective
par: Wen, Kaiyue, et autres
Publié: (2024)

Exploring End-to-end Differentiable Neural Charged Particle Tracking -- A Loss Landscape Perspective
par: Kortus, Tobias, et autres
Publié: (2024)

There is a Singularity in the Loss Landscape
par: Lowell, Mark
Publié: (2022)

Rényi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization
par: Zhang, Qiaozhe, et autres
Publié: (2025)

Paths and Ambient Spaces in Neural Loss Landscapes
par: Dold, Daniel, et autres
Publié: (2025)

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
par: Bushnaq, Lucius, et autres
Publié: (2024)

Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization
par: Peng, Danni, et autres
Publié: (2022)

LossLens: Diagnostics for Machine Learning through Loss Landscape Visual Analytics
par: Xie, Tiankai, et autres
Publié: (2024)

A PAC-Bayesian Link Between Generalisation and Flat Minima
par: Haddouche, Maxime, et autres
Publié: (2024)

Visualization and Analysis of the Loss Landscape in Graph Neural Networks
par: Moustafa, Samir, et autres
Publié: (2025)

Curvature-Aligned Probing for Local Loss-Landscape Stabilization
par: Kiselev, Nikita, et autres
Publié: (2026)

Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
par: Wang, Jinping, et autres
Publié: (2026)

Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis
par: Chen, Jiaqing, et autres
Publié: (2026)

Sharpness-Aware Minimization Can Hallucinate Minimizers
par: Park, Chanwoong, et autres
Publié: (2025)

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

Manifold Metric: A Loss Landscape Approach for Predicting Model Performance
par: Malviya, Pranshu, et autres
Publié: (2024)

Towards Robust Influence Functions with Flat Validation Minima
par: Ye, Xichen, et autres
Publié: (2025)

Unveiling the Basin-Like Loss Landscape in Large Language Models
par: Chen, Huanran, et autres
Publié: (2025)