{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"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":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"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":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"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":"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":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107},{"id":"2303.10353","title":"Sharpness-Aware Gradient Matching for Domain Generalization","created":"2023-03-18","cited_by_count":102},{"id":"1711.01530","title":"Fisher-Rao Metric, Geometry, and Complexity of Neural Networks","created":"2017-11-05","cited_by_count":100},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95},{"id":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86},{"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":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70},{"id":"2211.05729","title":"How Does Sharpness-Aware Minimization Minimize Sharpness?","created":"2022-11-10","cited_by_count":65},{"id":"1901.04653","title":"Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis","created":"2019-01-15","cited_by_count":59},{"id":"2210.03294","title":"Understanding Edge-of-Stability Training Dynamics with a Minimalist Example","created":"2022-10-07","cited_by_count":56},{"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},{"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},{"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":"2305.16292","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","created":"2023-05-25","cited_by_count":38},{"id":"2201.11968","title":"Training invariances and the low-rank phenomenon: beyond linear networks","created":"2022-01-28","cited_by_count":33},{"id":"2303.11242","title":"Make Landscape Flatter in Differentially Private Federated Learning","created":"2023-03-20","cited_by_count":33},{"id":"1806.00952","title":"Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization","created":"2018-06-04","cited_by_count":29},{"id":"2302.08692","title":"SAM operates far from home: eigenvalue regularization as a dynamical phenomenon","created":"2023-02-17","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":"2303.00565","title":"AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks","created":"2023-03-01","cited_by_count":21},{"id":"2110.06084","title":"Implicit Bias of Linear Equivariant Networks","created":"2021-10-12","cited_by_count":19},{"id":"2309.12488","title":"Sharpness-Aware Minimization and the Edge of Stability","created":"2023-09-21","cited_by_count":17},{"id":"2203.09962","title":"Randomized Sharpness-Aware Training for Boosting Computational Efficiency in Deep Learning","created":"2022-03-18","cited_by_count":14},{"id":"2212.05956","title":"Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging","created":"2022-12-12","cited_by_count":9},{"id":"2302.10181","title":"Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization","created":"2023-01-27","cited_by_count":9},{"id":"2212.04343","title":"Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization","created":"2022-12-07","cited_by_count":5},{"id":"2302.11836","title":"On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees","created":"2023-02-23","cited_by_count":5}],"next_cursor":null}