{"total":97,"rows":[{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58,"area":null},{"id":"2210.01513","title":"The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima","created":"2022-10-04","cited_by_count":51,"area":null},{"id":"2210.05497","title":"Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models","created":"2022-10-11","cited_by_count":42,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2210.01620","title":"SAM as an Optimal Relaxation of Bayes","created":"2022-10-04","cited_by_count":41,"area":null},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40,"area":null},{"id":"2212.09744","title":"DSI++: Updating Transformer Memory with New Documents","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2212.13827","title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","created":"2022-12-28","cited_by_count":28,"area":null},{"id":"2310.07269","title":"Why Does Sharpness-Aware Minimization Generalize Better Than SGD?","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2306.04226","title":"Normalization Layers Are All That Sharpness-Aware Minimization Needs","created":"2023-06-07","cited_by_count":27,"area":null},{"id":"2305.15287","title":"The Crucial Role of Normalization in Sharpness-Aware Minimization","created":"2023-05-24","cited_by_count":26,"area":null},{"id":"2302.08692","title":"SAM operates far from home: eigenvalue regularization as a dynamical phenomenon","created":"2023-02-17","cited_by_count":24,"area":null},{"id":"2402.15152","title":"On the Duality Between Sharpness-Aware Minimization and Adversarial Training","created":"2024-02-23","cited_by_count":24,"area":null},{"id":"2410.10373","title":"Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training","created":"2024-10-14","cited_by_count":24,"area":null},{"id":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22,"area":null},{"id":"2205.12694","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2306.09850","title":"Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima","created":"2023-06-16","cited_by_count":20,"area":null},{"id":"2305.15817","title":"Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term","created":"2023-05-25","cited_by_count":16,"area":null},{"id":"2209.07959","title":"Towards Bridging the Performance Gaps of Joint Energy-based Models","created":"2022-09-16","cited_by_count":15,"area":null},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2502.12340","title":"Understanding Silent Data Corruption in LLM Training","created":"2025-02-17","cited_by_count":15,"area":null},{"id":"2203.09962","title":"Randomized Sharpness-Aware Training for Boosting Computational Efficiency in Deep Learning","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2305.05392","title":"Sharpness-Aware Minimization Alone can Improve Adversarial Robustness","created":"2023-05-09","cited_by_count":14,"area":null},{"id":"2306.05651","title":"Differentially Private Sharpness-Aware Training","created":"2023-06-09","cited_by_count":14,"area":null},{"id":"2401.12033","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","created":"2024-01-22","cited_by_count":14,"area":null},{"id":"2406.03682","title":"A Universal Class of Sharpness-Aware Minimization Algorithms","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2305.15659","title":"How to escape sharp minima with random perturbations","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2410.12178","title":"Model Balancing Helps Low-data Training and Fine-tuning","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2210.12864","title":"K-SAM: Sharpness-Aware Minimization at the Speed of SGD","created":"2022-10-23","cited_by_count":10,"area":null},{"id":"2302.02713","title":"Flat Seeking Bayesian Neural Networks","created":"2023-02-06","cited_by_count":10,"area":null},{"id":"2302.09693","title":"mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization","created":"2023-02-19","cited_by_count":10,"area":null},{"id":"2312.13555","title":"CR-SAM: Curvature Regularized Sharpness-Aware Minimization","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2410.14802","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2412.13573","title":"Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2305.19953","title":"Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2405.20439","title":"Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2401.07250","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","created":"2024-01-14","cited_by_count":8,"area":null},{"id":"2410.10683","title":"SAMPa: Sharpness-aware Minimization Parallelized","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2406.13137","title":"Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2112.08772","title":"Sharpness-Aware Minimization with Dynamic Reweighting","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2310.03646","title":"TRAM: Bridging Trust Regions and Sharpness Aware Minimization","created":"2023-10-05","cited_by_count":6,"area":null},{"id":"2310.05401","title":"Entropy-MCMC: Sampling from Flat Basins with Ease","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2505.06527","title":"Improving Generalization of Medical Image Registration Foundation Model","created":"2025-05-10","cited_by_count":6,"area":null},{"id":"2212.04343","title":"Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2302.11836","title":"On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2306.04178","title":"Optimal Transport Model Distributional Robustness","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2406.08001","title":"Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2410.04196","title":"Improving Generalization with Flat Hilbert Bayesian Inference","created":"2024-10-05","cited_by_count":5,"area":null},{"id":"2506.06866","title":"SAFE: Finding Sparse and Flat Minima to Improve Pruning","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2306.17504","title":"Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2407.12993","title":"Improving SAM Requires Rethinking its Optimization Formulation","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2511.03548","title":"Flat Minima and Generalization: Insights from Stochastic Convex Optimization","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2305.13066","title":"Biomedical Named Entity Recognition via Dictionary-based Synonym Generalization","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2306.07052","title":"Gradient Ascent Post-training Enhances Language Model Generalization","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2312.04032","title":"RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2408.04065","title":"Do Sharpness-based Optimizers Improve Generalization in Medical Image Analysis?","created":"2024-08-07","cited_by_count":3,"area":null},{"id":"2502.18153","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2506.07247","title":"Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2208.06915","title":"Model Generalization: A Sharpness Aware Optimization Perspective","created":"2022-08-14","cited_by_count":2,"area":null},{"id":"2306.09121","title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2406.07107","title":"Agnostic Sharpness-Aware Minimization","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2409.09645","title":"COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2505.23866","title":"Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2507.04059","title":"Attributing Data for Sharpness-Aware Minimization","created":"2025-07-05","cited_by_count":2,"area":null},{"id":"2510.24919","title":"Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2303.02357","title":"DiTTO: A Feature Representation Imitation Approach for Improving Cross-Lingual Transfer","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2305.10252","title":"Sharpness & Shift-Aware Self-Supervised Learning","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2403.13204","title":"Diversity-Aware Agnostic Ensemble of Sharpness Minimizers","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2404.00758","title":"From Robustness to Improved Generalization and Calibration in Pre-trained Language Models","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2408.08222","title":"Enhancing Sharpness-Aware Minimization by Learning Perturbation Radius","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2501.11584","title":"GCSAM: Gradient Centralized Sharpness Aware Minimization","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2506.04690","title":"Towards Better Generalization via Distributional Input Projection Network","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2507.07883","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2508.16973","title":"Balanced Sharpness-Aware Minimization for Imbalanced Regression","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2602.09395","title":"Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2605.08894","title":"Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.29153","title":"Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2308.03236","title":"G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2309.17215","title":"Sharpness-Aware Teleportation on Riemannian Manifolds","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2311.09671","title":"Generalization Bounds for Robust Contrastive Learning: From Theory to Practice","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2404.07696","title":"Flatness Improves Backbone Generalisation in Few-shot Classification","created":"2024-04-11","cited_by_count":0,"area":null},{"id":"2404.12925","title":"A Hybrid Generative and Discriminative PointNet on Unordered Point Sets","created":"2024-04-19","cited_by_count":0,"area":null},{"id":"2406.06700","title":"Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2503.16550","title":"Unified Enhancement of the Generalization and Robustness of Language Models via Bi-Stage Optimization","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2508.10435","title":"Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2510.16157","title":"Zeroth-Order Sharpness-Aware Learning with Exponential Tilting","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2601.10251","title":"X-SAM: Boosting Sharpness-Aware Minimization with Dominant-Eigenvector Gradient Correction","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2603.10048","title":"Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2606.20814","title":"What Shapes Emergent Misalignment? Insights from Training Dynamics, Model Priors, and Data","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.17575","title":"Temperon: Full-Time SAM Quality at a Third Less Wall-Clock","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}