Imagen de Portada

A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chang, Wei-Kai, Khanna, Rajiv
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Why Some Models Resist Unlearning: A Linear Stability Perspective
por: Chang, Wei-Kai, et al.
Publicado: (2026)

Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
por: Chang, Wei-Kai, et al.
Publicado: (2025)

A Precise Characterization of SGD Stability Using Loss Surface Geometry
por: Dexter, Gregory, et al.
Publicado: (2024)

A Compression Perspective on Simplicity Bias
por: Marty, Tom, et al.
Publicado: (2026)

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
por: Bombari, Simone, et al.
Publicado: (2025)

Increasing Missingness to Reduce Bias: Richardson-SGD with Missing Data
por: Genans, Ferdinand, et al.
Publicado: (2026)

Sharpness-Aware Machine Unlearning
por: Tang, Haoran, et al.
Publicado: (2025)

From Logits to Latents: Contrastive Representation Shaping for LLM Unlearning
por: Tang, Haoran, et al.
Publicado: (2026)

Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data
por: Tsoy, Nikita, et al.
Publicado: (2024)

Exact Mean Square Linear Stability Analysis for SGD
por: Mulayoff, Rotem, et al.
Publicado: (2023)

Bias-Optimal Bounds for SGD: A Computer-Aided Lyapunov Analysis
por: Cortild, Daniel, et al.
Publicado: (2025)

Hierarchical Simplicity Bias of Neural Networks
por: Du, Zhehang
Publicado: (2023)

To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters
por: Dragutinović, Sara, et al.
Publicado: (2026)

SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
por: Kovalev, Dmitry
Publicado: (2025)

Comparing Spectral Bias and Robustness For Two-Layer Neural Networks: SGD vs Adaptive Random Fourier Features
por: Kammonen, Aku, et al.
Publicado: (2024)

Simplicity Bias via Global Convergence of Sharpness Minimization
por: Gatmiry, Khashayar, et al.
Publicado: (2024)

Stability and Generalization for Decentralized Markov SGD
por: Wang, Jiahuan, et al.
Publicado: (2026)

The Rich and the Simple: On the Implicit Bias of Adam and SGD
por: Vasudeva, Bhavya, et al.
Publicado: (2025)

Emergence and scaling laws in SGD learning of shallow neural networks
por: Ren, Yunwei, et al.
Publicado: (2025)

Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures
por: Zhang, Yedi, et al.
Publicado: (2025)

Masked Autoencoders that Feel the Heart: Unveiling Simplicity Bias for ECG Analyses
por: Xu, He-Yang, et al.
Publicado: (2025)

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
por: Vyas, Nikhil, et al.
Publicado: (2023)

Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
por: Sander, Tom, et al.
Publicado: (2024)

Byzantine-Robust Distributed SGD: A Unified Analysis and Tight Error Bounds
por: Ruan, Boyuan, et al.
Publicado: (2026)

Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates
por: Kovalev, Dmitry, et al.
Publicado: (2025)

Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
por: Jain, Anchit, et al.
Publicado: (2024)

Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD
por: Emmanouilidis, Konstantinos, et al.
Publicado: (2026)

Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
por: Nguyen, Dang, et al.
Publicado: (2024)

Bootstrap SGD: Algorithmic Stability and Robustness
por: Christmann, Andreas, et al.
Publicado: (2024)

Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics
por: Ren, Yi, et al.
Publicado: (2024)

Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
por: Andreyev, Arseniy, et al.
Publicado: (2024)

Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
por: Bars, Batiste Le, et al.
Publicado: (2023)

SAMOSA: Sharpness Aware Minimization for Open Set Active learning
por: Kim, Young In, et al.
Publicado: (2025)

Do Quantum Neural Networks have Simplicity Bias?
por: Pointing, Jessica
Publicado: (2024)

Ordered Momentum for Asynchronous SGD
por: Shi, Chang-Wei, et al.
Publicado: (2024)

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning
por: Lee, Hojoon, et al.
Publicado: (2024)

On the Emergence of Weak-to-Strong Generalization: A Bias-Variance Perspective
por: Xu, Gengze, et al.
Publicado: (2025)

On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials
por: Mulayoff, Rotem, et al.
Publicado: (2026)

Structure-Aware Spectral Sparsification via Uniform Edge Sampling
por: He, Kaiwen, et al.
Publicado: (2025)

The Space Complexity of Approximating Logistic Loss
por: Dexter, Gregory, et al.
Publicado: (2024)