{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"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":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"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":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"1406.2572","title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","created":"2014-06-10","cited_by_count":289},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"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":"1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","created":"2019-05-29","cited_by_count":217},{"id":"2006.00719","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","created":"2020-06-01","cited_by_count":202},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"1706.03662","title":"Practical Gauss-Newton Optimisation for Deep Learning","created":"2017-06-12","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":"2010.05627","title":"Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning","created":"2020-10-12","cited_by_count":126},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"2304.13972","title":"Convergence of Adam Under Relaxed Assumptions","created":"2023-04-27","cited_by_count":99},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95},{"id":"1807.05031","title":"On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length","created":"2018-07-13","cited_by_count":88},{"id":"1705.07485","title":"Shake-Shake regularization","created":"2017-05-21","cited_by_count":87},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70},{"id":"1401.7020","title":"A Stochastic Quasi-Newton Method for Large-Scale Optimization","created":"2014-01-27","cited_by_count":69},{"id":"2006.08877","title":"Practical Quasi-Newton Methods for Training Deep Neural Networks","created":"2020-06-16","cited_by_count":68},{"id":"2006.11316","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","created":"2020-06-19","cited_by_count":50},{"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":"1502.04390","title":"Equilibrated adaptive learning rates for non-convex optimization","created":"2015-02-15","cited_by_count":42},{"id":"2202.02831","title":"Anticorrelated Noise Injection for Improved Generalization","created":"2022-02-06","cited_by_count":42},{"id":"1708.07827","title":"Second-Order Optimization for Non-Convex Machine Learning: An Empirical Study","created":"2017-08-25","cited_by_count":35},{"id":"2006.10732","title":"When Does Preconditioning Help or Hurt Generalization?","created":"2020-06-18","cited_by_count":31},{"id":"1603.09649","title":"Stochastic Block BFGS: Squeezing More Curvature out of Data","created":"2016-03-31","cited_by_count":24},{"id":"2302.08692","title":"SAM operates far from home: eigenvalue regularization as a dynamical phenomenon","created":"2023-02-17","cited_by_count":24},{"id":"2405.03676","title":"Why is SAM Robust to Label Noise?","created":"2024-05-06","cited_by_count":21},{"id":"2008.07545","title":"Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization","created":"2020-08-17","cited_by_count":15},{"id":"2212.00781","title":"Second-order optimization with lazy Hessians","created":"2022-12-01","cited_by_count":15},{"id":"2401.08060","title":"Fundamental Convergence Analysis of Sharpness-Aware Minimization","created":"2024-01-16","cited_by_count":14},{"id":"2401.12033","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","created":"2024-01-22","cited_by_count":14},{"id":"2405.16397","title":"AdaFisher: Adaptive Second Order Optimization via Fisher Information","created":"2024-05-26","cited_by_count":14},{"id":"1301.3641","title":"Training Neural Networks with Stochastic Hessian-Free Optimization","created":"2013-01-16","cited_by_count":9},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3}],"next_cursor":null}