{"list":"other","total":61,"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"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":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"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":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"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":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146},{"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":"2010.05627","title":"Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning","created":"2020-10-12","cited_by_count":126},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122},{"id":"1802.06175","title":"An Alternative View: When Does SGD Escape Local Minima?","created":"2018-02-17","cited_by_count":115},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"1910.05446","title":"On Empirical Comparisons of Optimizers for Deep Learning","created":"2019-10-11","cited_by_count":103},{"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":"2206.04920","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":"1705.10412","title":"Gradient Descent Can Take Exponential Time to Escape Saddle Points","created":"2017-05-29","cited_by_count":74},{"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":"2012.14193","title":"Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization","created":"2020-12-28","cited_by_count":62},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57},{"id":"2306.07179","title":"Benchmarking Neural Network Training Algorithms","created":"2023-06-12","cited_by_count":52},{"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":"1901.08168","title":"Loss Landscapes of Regularized Linear Autoencoders","created":"2019-01-23","cited_by_count":46},{"id":"2304.14647","title":"An Adaptive Policy to Employ Sharpness-Aware Minimization","created":"2023-04-28","cited_by_count":43},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","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":"2308.07815","title":"ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition","created":"2023-08-15","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":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22},{"id":"2309.12488","title":"Sharpness-Aware Minimization and the Edge of Stability","created":"2023-09-21","cited_by_count":17},{"id":"2305.15817","title":"Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term","created":"2023-05-25","cited_by_count":16},{"id":"2203.09962","title":"Randomized Sharpness-Aware Training for Boosting Computational Efficiency in Deep Learning","created":"2022-03-18","cited_by_count":14},{"id":"2301.06308","title":"Stability Analysis of Sharpness-Aware Minimization","created":"2023-01-16","cited_by_count":14},{"id":"2305.05392","title":"Sharpness-Aware Minimization Alone can Improve Adversarial Robustness","created":"2023-05-09","cited_by_count":14},{"id":"2210.06895","title":"GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization","created":"2022-10-13","cited_by_count":13},{"id":"2210.12864","title":"K-SAM: Sharpness-Aware Minimization at the Speed of SGD","created":"2022-10-23","cited_by_count":10},{"id":"1906.10822","title":"Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD","created":"2019-06-26","cited_by_count":7},{"id":"2112.08772","title":"Sharpness-Aware Minimization with Dynamic Reweighting","created":"2021-12-16","cited_by_count":6},{"id":"2110.13265","title":"On the Second-order Convergence Properties of Random Search Methods","created":"2021-10-25","cited_by_count":5}],"next_cursor":null}