{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1904.03758","title":"Meta-Learning with Differentiable Convex Optimization","created":"2019-04-07","cited_by_count":461},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"1805.08136","title":"Meta-learning with differentiable closed-form solvers","created":"2018-05-21","cited_by_count":397},{"id":"2109.12298","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","created":"2021-09-25","cited_by_count":383},{"id":"1909.09157","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","created":"2019-09-19","cited_by_count":359},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1703.00837","title":"Meta Networks","created":"2017-03-02","cited_by_count":269},{"id":"1806.02817","title":"Probabilistic Model-Agnostic Meta-Learning","created":"2018-06-07","cited_by_count":256},{"id":"1810.03548","title":"Meta-Learning: A Survey","created":"2018-10-08","cited_by_count":256},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"1906.02717","title":"Adaptive Gradient-Based Meta-Learning Methods","created":"2019-06-06","cited_by_count":183},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"1902.08438","title":"Online Meta-Learning","created":"2019-02-22","cited_by_count":137},{"id":"1908.10400","title":"On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms","created":"2019-08-27","cited_by_count":132},{"id":"1902.08142","title":"Evaluating the Search Phase of Neural Architecture Search","created":"2019-02-21","cited_by_count":120},{"id":"2108.04392","title":"Rethinking Architecture Selection in Differentiable NAS","created":"2021-08-10","cited_by_count":92},{"id":"1911.11090","title":"Meta-Learning of Neural Architectures for Few-Shot Learning","created":"2019-11-25","cited_by_count":73},{"id":"1902.10644","title":"Provable Guarantees for Gradient-Based Meta-Learning","created":"2019-02-27","cited_by_count":67},{"id":"1805.07513","title":"Diverse Few-Shot Text Classification with Multiple Metrics","created":"2018-05-19","cited_by_count":61},{"id":"1911.03863","title":"Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks","created":"2019-11-10","cited_by_count":57},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52},{"id":"2106.09017","title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","created":"2021-06-16","cited_by_count":50},{"id":"2111.13293","title":"KNAS: Green Neural Architecture Search","created":"2021-11-26","cited_by_count":33},{"id":"2010.05843","title":"How Important is the Train-Validation Split in Meta-Learning?","created":"2020-10-12","cited_by_count":30},{"id":"2002.07836","title":"Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning","created":"2020-02-18","cited_by_count":28},{"id":"2006.13182","title":"On the Global Optimality of Model-Agnostic Meta-Learning","created":"2020-06-23","cited_by_count":21},{"id":"1910.02875","title":"The asymptotic spectrum of the Hessian of DNN throughout training","created":"2019-10-01","cited_by_count":19},{"id":"1912.13053","title":"Disentangling Trainability and Generalization in Deep Neural Networks","created":"2019-12-30","cited_by_count":16},{"id":"1806.06927","title":"Auto-Meta: Automated Gradient Based Meta Learner Search","created":"2018-06-11","cited_by_count":14},{"id":"1901.00279","title":"Elimination of All Bad Local Minima in Deep Learning","created":"2019-01-02","cited_by_count":10},{"id":"2006.10921","title":"Meta Learning in the Continuous Time Limit","created":"2020-06-19","cited_by_count":10}],"next_cursor":null}