{"list":"other","total":61,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"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":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1907.04502","title":"DeepXDE: A deep learning library for solving differential equations","created":"2019-07-10","cited_by_count":619},{"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":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"1711.10561","title":"Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations","created":"2017-11-28","cited_by_count":373},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"1711.11157","title":"A Semantic Loss Function for Deep Learning with Symbolic Knowledge","created":"2017-11-29","cited_by_count":270},{"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":"1903.12394","title":"Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems","created":"2019-03-29","cited_by_count":205},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2002.04083","title":"Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations","created":"2020-02-10","cited_by_count":155},{"id":"1902.04760","title":"Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation","created":"2019-02-13","cited_by_count":149},{"id":"1901.05353","title":"A Primer on PAC-Bayesian Learning","created":"2019-01-16","cited_by_count":132},{"id":"1710.11431","title":"Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling","created":"2017-10-31","cited_by_count":131},{"id":"1810.05369","title":"Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel","created":"2018-10-12","cited_by_count":131},{"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":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"1909.12292","title":"Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks","created":"2019-09-26","cited_by_count":121},{"id":"1705.09412","title":"Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management","created":"2017-05-26","cited_by_count":96},{"id":"2010.04456","title":"Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting","created":"2020-10-09","cited_by_count":95},{"id":"1605.08636","title":"PAC-Bayesian Theory Meets Bayesian Inference","created":"2016-05-27","cited_by_count":88},{"id":"1911.12360","title":"How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?","created":"2019-11-27","cited_by_count":84},{"id":"1711.01244","title":"Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory","created":"2017-11-03","cited_by_count":76},{"id":"1802.05313","title":"Reinforcement Learning from Imperfect Demonstrations","created":"2018-02-14","cited_by_count":75},{"id":"2002.12915","title":"The Implicit and Explicit Regularization Effects of Dropout","created":"2020-02-28","cited_by_count":71},{"id":"1709.05963","title":"Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations","created":"2017-09-18","cited_by_count":65},{"id":"1612.04844","title":"The More You Know: Using Knowledge Graphs for Image Classification","created":"2016-12-14","cited_by_count":63},{"id":"1710.04725","title":"Hyperparameter Importance Across Datasets","created":"2017-10-12","cited_by_count":63},{"id":"1902.01384","title":"Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks","created":"2019-02-04","cited_by_count":60},{"id":"1807.10025","title":"Towards Optimal Power Control via Ensembling Deep Neural Networks","created":"2018-07-26","cited_by_count":38},{"id":"1902.02647","title":"Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both?","created":"2019-02-05","cited_by_count":38},{"id":"1806.06029","title":"One-Shot Unsupervised Cross Domain Translation","created":"2018-06-15","cited_by_count":35},{"id":"1810.11730","title":"Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks","created":"2018-10-27","cited_by_count":35},{"id":"2010.10090","title":"Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher","created":"2020-10-20","cited_by_count":33},{"id":"1808.01486","title":"Spatial Deep Learning for Wireless Scheduling","created":"2018-08-04","cited_by_count":32},{"id":"2004.01806","title":"On the convergence of physics informed neural networks for linear second-order elliptic and parabolic type PDEs","created":"2020-04-03","cited_by_count":31},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29},{"id":"2111.01875","title":"Subquadratic Overparameterization for Shallow Neural Networks","created":"2021-11-02","cited_by_count":26},{"id":"1807.10916","title":"Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data","created":"2018-07-28","cited_by_count":25},{"id":"1905.09870","title":"Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems","created":"2019-05-23","cited_by_count":24},{"id":"2106.05370","title":"5G MIMO Data for Machine Learning: Application to Beam-Selection using Deep Learning","created":"2021-06-09","cited_by_count":20},{"id":"2002.08483","title":"Strength from Weakness: Fast Learning Using Weak Supervision","created":"2020-02-19","cited_by_count":18},{"id":"2110.05645","title":"A global convergence theory for deep ReLU implicit networks via over-parameterization","created":"2021-10-11","cited_by_count":17},{"id":"2005.10691","title":"Improving Deep Learning Models via Constraint-Based Domain Knowledge: a Brief Survey","created":"2020-05-19","cited_by_count":16},{"id":"2004.05020","title":"ModuleNet: Knowledge-inherited Neural Architecture Search","created":"2020-04-10","cited_by_count":11},{"id":"2002.10742","title":"Injecting Domain Knowledge in Neural Networks: a Controlled Experiment on a Constrained Problem","created":"2020-02-25","cited_by_count":7},{"id":"1907.01068","title":"Augmenting and Tuning Knowledge Graph Embeddings","created":"2019-07-01","cited_by_count":4}],"next_cursor":null}