{"list":"other","total":51,"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":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"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":"1708.07469","title":"DGM: A deep learning algorithm for solving partial differential equations","created":"2017-08-24","cited_by_count":678},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"2007.14527","title":"When and why PINNs fail to train: A neural tangent kernel perspective","created":"2020-07-28","cited_by_count":634},{"id":"1710.00211","title":"The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems","created":"2017-09-30","cited_by_count":583},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"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":"1707.02568","title":"Solving high-dimensional partial differential equations using deep learning","created":"2017-07-09","cited_by_count":556},{"id":"1901.06523","title":"Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks","created":"2019-01-19","cited_by_count":368},{"id":"1911.13225","title":"DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing","created":"2019-11-29","cited_by_count":180},{"id":"1912.01198","title":"Towards Understanding the Spectral Bias of Deep Learning","created":"2019-12-03","cited_by_count":174},{"id":"1802.03620","title":"Optimal approximation of continuous functions by very deep ReLU networks","created":"2018-02-10","cited_by_count":166},{"id":"2001.03040","title":"Deep Network Approximation for Smooth Functions","created":"2020-01-09","cited_by_count":164},{"id":"1611.00740","title":"Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review","created":"2016-11-02","cited_by_count":155},{"id":"1912.03207","title":"NASA: Neural Articulated Shape Approximation","created":"2019-12-06","cited_by_count":149},{"id":"1711.06464","title":"A unified deep artificial neural network approach to partial differential equations in complex geometries","created":"2017-11-17","cited_by_count":122},{"id":"1906.05497","title":"Deep Network Approximation Characterized by Number of Neurons","created":"2019-06-13","cited_by_count":122},{"id":"1906.09477","title":"The phase diagram of approximation rates for deep neural networks","created":"2019-06-22","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":"2007.11207","title":"Multi-scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains","created":"2020-07-22","cited_by_count":79},{"id":"1810.06397","title":"A Priori Estimates of the Population Risk for Two-layer Neural Networks","created":"2018-10-15","cited_by_count":76},{"id":"2004.01902","title":"Rational neural networks","created":"2020-04-04","cited_by_count":75},{"id":"2010.14075","title":"Neural Network Approximation: Three Hidden Layers Are Enough","created":"2020-10-25","cited_by_count":63},{"id":"1909.05215","title":"Reconstructing continuous distributions of 3D protein structure from cryo-EM images","created":"2019-09-11","cited_by_count":56},{"id":"1906.11945","title":"Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theorem","created":"2019-06-27","cited_by_count":49},{"id":"1906.09235","title":"Theory of the Frequency Principle for General Deep Neural Networks","created":"2019-06-21","cited_by_count":46},{"id":"1809.03062","title":"Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations","created":"2018-09-09","cited_by_count":45},{"id":"1811.01165","title":"Convergence of the Deep BSDE Method for Coupled FBSDEs","created":"2018-11-03","cited_by_count":43},{"id":"2006.15733","title":"Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory","created":"2020-06-28","cited_by_count":41},{"id":"1907.05317","title":"Adaptive Deep Learning for High-Dimensional Hamilton-Jacobi-Bellman Equations","created":"2019-07-11","cited_by_count":40},{"id":"1705.03071","title":"Geometry of Optimization and Implicit Regularization in Deep Learning","created":"2017-05-08","cited_by_count":39},{"id":"1807.00297","title":"Exponential Convergence of the Deep Neural Network Approximation for Analytic Functions","created":"2018-07-01","cited_by_count":38},{"id":"1909.11759","title":"A Phase Shift Deep Neural Network for High Frequency Approximation and Wave Problems","created":"2019-09-23","cited_by_count":35},{"id":"2002.02600","title":"Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach","created":"2020-02-07","cited_by_count":35},{"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":"1911.02109","title":"Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs","created":"2019-11-05","cited_by_count":28},{"id":"1903.02154","title":"A Priori Estimates of the Population Risk for Residual Networks","created":"2019-03-06","cited_by_count":14},{"id":"1812.00542","title":"Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent","created":"2018-12-03","cited_by_count":6},{"id":"1811.00659","title":"Implicit Regularization of Stochastic Gradient Descent in Natural Language Processing: Observations and Implications","created":"2018-11-01","cited_by_count":4},{"id":"1911.01612","title":"Quasi-Monte Carlo sampling for machine-learning partial differential equations","created":"2019-11-05","cited_by_count":2}],"next_cursor":null}