Copertina

Sharp Minima Can Generalize: A Loss Landscape Perspective On Data

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fan, Raymond, Sandlund, Bryce, Ko, Lin Myat
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Function-Centric Perspective on Flat and Sharp Minima
di: Mason-Williams, Israel, et al.
Pubblicazione: (2025)

Sharpness of Minima in Deep Matrix Factorization
di: Kamber, Anil, et al.
Pubblicazione: (2025)

Bilateral Sharpness-Aware Minimization for Flatter Minima
di: Deng, Jiaxin, et al.
Pubblicazione: (2024)

On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness
di: Kamber, Anil, et al.
Pubblicazione: (2026)

Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
di: Zhou, Zhanpeng, et al.
Pubblicazione: (2024)

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
di: Chen, Huanran, et al.
Pubblicazione: (2026)

Model Merging on Loss Landscape: A Geometry Perspective
di: Lu, Juanwu, et al.
Pubblicazione: (2026)

Challenges in Training PINNs: A Loss Landscape Perspective
di: Rathore, Pratik, et al.
Pubblicazione: (2024)

Evaluating Loss Landscapes from a Topology Perspective
di: Xie, Tiankai, et al.
Pubblicazione: (2024)

Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
di: Fang, Kun, et al.
Pubblicazione: (2023)

A Flat Minima Perspective on Understanding Augmentations and Model Robustness
di: Yoo, Weebum, et al.
Pubblicazione: (2025)

Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization
di: Wu, Wenhan, et al.
Pubblicazione: (2025)

Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics
di: Jacobsen, Albert Kjøller, et al.
Pubblicazione: (2026)

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

Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
di: Jeon, Dongjae, et al.
Pubblicazione: (2024)

Sensitivity Analysis On Loss Landscape
di: Faroz, Salman
Pubblicazione: (2024)

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

Flat Minima and Generalization: Insights from Stochastic Convex Optimization
di: Schliserman, Matan, et al.
Pubblicazione: (2025)

Bringing the Discussion of Minima Sharpness to the Audio Domain: a Filter-Normalised Evaluation for Acoustic Scene Classification
di: Milling, Manuel, et al.
Pubblicazione: (2023)

Neural Network Plasticity and Loss Sharpness
di: Koster, Max, et al.
Pubblicazione: (2024)

Are Flat Minima an Illusion?
di: Bennett, Michael Timothy
Pubblicazione: (2026)

LSAM: Asynchronous Distributed Training with Landscape-Smoothed Sharpness-Aware Minimization
di: Teng, Yunfei, et al.
Pubblicazione: (2025)

Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective
di: Wen, Kaiyue, et al.
Pubblicazione: (2024)

Exploring End-to-end Differentiable Neural Charged Particle Tracking -- A Loss Landscape Perspective
di: Kortus, Tobias, et al.
Pubblicazione: (2024)

There is a Singularity in the Loss Landscape
di: Lowell, Mark
Pubblicazione: (2022)

Rényi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization
di: Zhang, Qiaozhe, et al.
Pubblicazione: (2025)

Paths and Ambient Spaces in Neural Loss Landscapes
di: Dold, Daniel, et al.
Pubblicazione: (2025)

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
di: Bushnaq, Lucius, et al.
Pubblicazione: (2024)

Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization
di: Peng, Danni, et al.
Pubblicazione: (2022)

LossLens: Diagnostics for Machine Learning through Loss Landscape Visual Analytics
di: Xie, Tiankai, et al.
Pubblicazione: (2024)

A PAC-Bayesian Link Between Generalisation and Flat Minima
di: Haddouche, Maxime, et al.
Pubblicazione: (2024)

Visualization and Analysis of the Loss Landscape in Graph Neural Networks
di: Moustafa, Samir, et al.
Pubblicazione: (2025)

Curvature-Aligned Probing for Local Loss-Landscape Stabilization
di: Kiselev, Nikita, et al.
Pubblicazione: (2026)

Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
di: Wang, Jinping, et al.
Pubblicazione: (2026)

Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis
di: Chen, Jiaqing, et al.
Pubblicazione: (2026)

Sharpness-Aware Minimization Can Hallucinate Minimizers
di: Park, Chanwoong, et al.
Pubblicazione: (2025)

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

Manifold Metric: A Loss Landscape Approach for Predicting Model Performance
di: Malviya, Pranshu, et al.
Pubblicazione: (2024)

Towards Robust Influence Functions with Flat Validation Minima
di: Ye, Xichen, et al.
Pubblicazione: (2025)

Unveiling the Basin-Like Loss Landscape in Large Language Models
di: Chen, Huanran, et al.
Pubblicazione: (2025)