{"list":"other","total":70,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1901.06053","title":"A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks","created":"2019-01-18","cited_by_count":214},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"2209.15594","title":"Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability","created":"2022-09-30","cited_by_count":155},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"1511.06251","title":"Stochastic modified equations and adaptive stochastic gradient algorithms","created":"2015-11-19","cited_by_count":142},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129},{"id":"2205.09745","title":"Understanding Gradient Descent on Edge of Stability in Deep Learning","created":"2022-05-19","cited_by_count":128},{"id":"1904.09080","title":"Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process","created":"2019-04-19","cited_by_count":123},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121},{"id":"1811.01558","title":"Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations","created":"2018-11-05","cited_by_count":114},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91},{"id":"2006.08680","title":"Shape Matters: Understanding the Implicit Bias of the Noise Covariance","created":"2020-06-15","cited_by_count":88},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73},{"id":"1803.05999","title":"Escaping Saddles with Stochastic Gradients","created":"2018-03-15","cited_by_count":66},{"id":"2211.05729","title":"How Does Sharpness-Aware Minimization Minimize Sharpness?","created":"2022-11-10","cited_by_count":65},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53},{"id":"1906.02613","title":"Bad Global Minima Exist and SGD Can Reach Them","created":"2019-06-06","cited_by_count":49},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49},{"id":"2210.01620","title":"SAM as an Optimal Relaxation of Bayes","created":"2022-10-04","cited_by_count":41},{"id":"2102.05375","title":"Strength of Minibatch Noise in SGD","created":"2021-02-10","cited_by_count":39},{"id":"2307.11007","title":"Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization","created":"2023-07-20","cited_by_count":39},{"id":"2309.15639","title":"Enhancing Sharpness-Aware Optimization Through Variance Suppression","created":"2023-09-27","cited_by_count":37},{"id":"2110.03128","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","created":"2021-10-07","cited_by_count":31},{"id":"2305.15287","title":"The Crucial Role of Normalization in Sharpness-Aware Minimization","created":"2023-05-24","cited_by_count":26},{"id":"2302.08692","title":"SAM operates far from home: eigenvalue regularization as a dynamical phenomenon","created":"2023-02-17","cited_by_count":24},{"id":"2410.10373","title":"Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training","created":"2024-10-14","cited_by_count":24},{"id":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22},{"id":"2501.12666","title":"Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization","created":"2025-01-22","cited_by_count":21},{"id":"2306.09850","title":"Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima","created":"2023-06-16","cited_by_count":20},{"id":"2412.01021","title":"On the Feature Learning in Diffusion Models","created":"2024-12-02","cited_by_count":20},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15},{"id":"2401.08060","title":"Fundamental Convergence Analysis of Sharpness-Aware Minimization","created":"2024-01-16","cited_by_count":14},{"id":"2406.03682","title":"A Universal Class of Sharpness-Aware Minimization Algorithms","created":"2024-06-06","cited_by_count":14},{"id":"2212.02083","title":"On the Overlooked Structure of Stochastic Gradients","created":"2022-12-05","cited_by_count":13},{"id":"2305.15659","title":"How to escape sharp minima with random perturbations","created":"2023-05-25","cited_by_count":13},{"id":"2410.04870","title":"On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent","created":"2024-10-07","cited_by_count":12},{"id":"2302.02713","title":"Flat Seeking Bayesian Neural Networks","created":"2023-02-06","cited_by_count":10},{"id":"2312.13555","title":"CR-SAM: Curvature Regularized Sharpness-Aware Minimization","created":"2023-12-21","cited_by_count":10},{"id":"2411.02837","title":"On the Comparison between Multi-modal and Single-modal Contrastive Learning","created":"2024-11-05","cited_by_count":10},{"id":"2503.02225","title":"Sharpness-Aware Minimization: General Analysis and Improved Rates","created":"2025-03-04","cited_by_count":10},{"id":"2405.20439","title":"Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning","created":"2024-05-30","cited_by_count":9},{"id":"2410.10683","title":"SAMPa: Sharpness-aware Minimization Parallelized","created":"2024-10-14","cited_by_count":8},{"id":"2502.02407","title":"Avoiding spurious sharpness minimization broadens applicability of SAM","created":"2025-02-04","cited_by_count":8},{"id":"2406.13137","title":"Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models","created":"2024-06-19","cited_by_count":7},{"id":"2212.04343","title":"Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization","created":"2022-12-07","cited_by_count":5},{"id":"2306.04178","title":"Optimal Transport Model Distributional Robustness","created":"2023-06-07","cited_by_count":5},{"id":"2307.16704","title":"Lookbehind-SAM: k steps back, 1 step forward","created":"2023-07-31","cited_by_count":5},{"id":"2410.04196","title":"Improving Generalization with Flat Hilbert Bayesian Inference","created":"2024-10-05","cited_by_count":5},{"id":"2406.07107","title":"Agnostic Sharpness-Aware Minimization","created":"2024-06-11","cited_by_count":2},{"id":"2509.02433","title":"VASSO: Variance Suppression for Sharpness-Aware Minimization","created":"2025-09-02","cited_by_count":1}],"next_cursor":null}