{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"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":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"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":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"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":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223},{"id":"1802.01396","title":"To understand deep learning we need to understand kernel learning","created":"2018-02-05","cited_by_count":187},{"id":"1712.06559","title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning","created":"2017-12-18","cited_by_count":150},{"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":"1810.07288","title":"Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron","created":"2018-10-16","cited_by_count":143},{"id":"2002.10542","title":"Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence","created":"2020-02-24","cited_by_count":137},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132},{"id":"2112.13492","title":"Vision Transformer for Small-Size Datasets","created":"2021-12-27","cited_by_count":122},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"id":"2003.01897","title":"Optimal Regularization Can Mitigate Double Descent","created":"2020-03-04","cited_by_count":109},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"1803.01206","title":"On the Power of Over-parametrization in Neural Networks with Quadratic Activation","created":"2018-03-03","cited_by_count":102},{"id":"1709.01953","title":"Implicit Regularization in Deep Learning","created":"2017-09-06","cited_by_count":90},{"id":"2010.00892","title":"Variance-Reduced Methods for Machine Learning","created":"2020-10-02","cited_by_count":79},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79},{"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":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68},{"id":"2207.02628","title":"The alignment property of SGD noise and how it helps select flat minima: A stability analysis","created":"2022-07-06","cited_by_count":64},{"id":"2006.11226","title":"Gradient descent follows the regularization path for general losses","created":"2020-06-19","cited_by_count":59},{"id":"2309.08520","title":"Scaling Laws for Sparsely-Connected Foundation Models","created":"2023-09-15","cited_by_count":43},{"id":"2202.02831","title":"Anticorrelated Noise Injection for Improved Generalization","created":"2022-02-06","cited_by_count":42},{"id":"2305.16292","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","created":"2023-05-25","cited_by_count":38},{"id":"1811.02564","title":"On exponential convergence of SGD in non-convex over-parametrized learning","created":"2018-11-06","cited_by_count":33},{"id":"2303.13087","title":"Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization","created":"2023-03-23","cited_by_count":29},{"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":"2306.09850","title":"Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima","created":"2023-06-16","cited_by_count":20},{"id":"1910.04920","title":"Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation","created":"2019-10-11","cited_by_count":18},{"id":"1712.08859","title":"Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence","created":"2017-12-23","cited_by_count":17},{"id":"2302.09693","title":"mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization","created":"2023-02-19","cited_by_count":10}],"next_cursor":null}