Image de couverture de livre

Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Moon, Chaewon, Si, Dongkuk, Yun, Chulhee
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
par: Kim, Yujun, et autres
Publié: (2025)

Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
par: Baek, Beomhan, et autres
Publié: (2025)

Implicit Bias and Loss of Plasticity in Matrix Completion: Depth Promotes Low-Rankness
par: Shin, Baekrok, et autres
Publié: (2026)

Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models
par: Cao, Tianxiao, et autres
Publié: (2025)

Provable Benefit of Cutout and CutMix for Feature Learning
par: Oh, Junsoo, et autres
Publié: (2024)

Stability Analysis of Sharpness-Aware Minimization
par: Kim, Hoki, et autres
Publié: (2023)

Navigating Potholes with Geometry-Aware Sharpness Minimization
par: Dufort-Labbé, Simon, et autres
Publié: (2026)

Membership Privacy Risks of Sharpness Aware Minimization
par: Kim, Young In, et autres
Publié: (2023)

Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization
par: Tan, Chengli, et autres
Publié: (2025)

Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
par: Chen, Jianlong, et autres
Publié: (2026)

SAMOSA: Sharpness Aware Minimization for Open Set Active learning
par: Kim, Young In, et autres
Publié: (2025)

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
par: Cho, Hanseul, et autres
Publié: (2024)

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
par: Shin, Baekrok, et autres
Publié: (2024)

Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty
par: Cho, Yeseul, et autres
Publié: (2025)

Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?
par: Kim, Jihwan, et autres
Publié: (2026)

X-SAM: Boosting Sharpness-Aware Minimization with Dominant-Eigenvector Gradient Correction
par: Duan, Hongru, et autres
Publié: (2026)

Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
par: Luo, Haocheng, et autres
Publié: (2026)

FairSAM: Fair Classification on Corrupted Data Through Sharpness-Aware Minimization
par: Dai, Yucong, et autres
Publié: (2025)

Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization
par: Schapiro, Samuel, et autres
Publié: (2024)

Attributing Data for Sharpness-Aware Minimization
par: Ren, Chenyang, et autres
Publié: (2025)

Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
par: Luo, Yihong, et autres
Publié: (2024)

Sharpness-Aware Minimization with Z-Score Gradient Filtering
par: Yun, Vincent-Daniel
Publié: (2025)

Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo
par: Kim, Hyunsu, et autres
Publié: (2025)

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
par: Jung, Hyunji, et autres
Publié: (2025)

Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization
par: Gu, Yujie, et autres
Publié: (2026)

Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
par: Liu, Yuhang, et autres
Publié: (2025)

Enhancing Robustness of Offline Reinforcement Learning Under Data Corruption via Sharpness-Aware Minimization
par: Xu, Le, et autres
Publié: (2025)

Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
par: Yoo, Geonhui, et autres
Publié: (2025)

Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
par: Song, Minhak, et autres
Publié: (2025)

On the Duality Between Sharpness-Aware Minimization and Adversarial Training
par: Zhang, Yihao, et autres
Publié: (2024)

Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy
par: Tan, Chengli, et autres
Publié: (2024)

Sharpness-Aware Teleportation on Riemannian Manifolds
par: Truong, Tuan, et autres
Publié: (2023)

Sharpness-Aware Black-Box Optimization
par: Ye, Feiyang, et autres
Publié: (2024)

Locality-Aware Redundancy Pruning for LLM Depth Compression
par: Yun, Vincent-Daniel, et autres
Publié: (2026)

Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
par: Xu, Jian, et autres
Publié: (2024)

Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
par: Chen, Zihao, et autres
Publié: (2025)

Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts
par: Maxson, Taylor, et autres
Publié: (2026)

Implicit Bias of the JKO Scheme
par: Halmos, Peter, et autres
Publié: (2025)

NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
par: Xu, Jiayu, et autres
Publié: (2026)

Tractable Sharpness-Aware Learning of Probabilistic Circuits
par: Suresh, Hrithik, et autres
Publié: (2025)