{"list":"other","total":67,"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"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":"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":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"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":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"id":"1805.09545","title":"On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport","created":"2018-05-24","cited_by_count":426},{"id":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1810.09538","title":"Pyro: Deep Universal Probabilistic Programming","created":"2018-10-18","cited_by_count":380},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1709.02540","title":"The Expressive Power of Neural Networks: A View from the Width","created":"2017-09-08","cited_by_count":320},{"id":"1804.11271","title":"Gaussian Process Behaviour in Wide Deep Neural Networks","created":"2018-04-30","cited_by_count":317},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"1602.04485","title":"Benefits of depth in neural networks","created":"2016-02-14","cited_by_count":250},{"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":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"2010.15110","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","created":"2020-10-28","cited_by_count":187},{"id":"1810.05148","title":"Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes","created":"2018-10-11","cited_by_count":167},{"id":"2007.15801","title":"Finite Versus Infinite Neural Networks: an Empirical Study","created":"2020-07-31","cited_by_count":157},{"id":"1910.12478","title":"Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes","created":"2019-10-28","cited_by_count":151},{"id":"2006.13409","title":"When Do Neural Networks Outperform Kernel Methods?","created":"2020-06-24","cited_by_count":150},{"id":"1705.08933","title":"Doubly Stochastic Variational Inference for Deep Gaussian Processes","created":"2017-05-24","cited_by_count":143},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"1808.05587","title":"Deep Convolutional Networks as shallow Gaussian Processes","created":"2018-08-16","cited_by_count":138},{"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":"1707.04926","title":"Theoretical insights into the optimization landscape of over-parameterized shallow neural networks","created":"2017-07-16","cited_by_count":128},{"id":"2006.10540","title":"Infinite attention: NNGP and NTK for deep attention networks","created":"2020-06-18","cited_by_count":121},{"id":"1904.00687","title":"On the Power and Limitations of Random Features for Understanding Neural Networks","created":"2019-04-01","cited_by_count":103},{"id":"1905.10337","title":"What Can ResNet Learn Efficiently, Going Beyond Kernels?","created":"2019-05-24","cited_by_count":91},{"id":"1906.08899","title":"Limitations of Lazy Training of Two-layers Neural Networks","created":"2019-06-21","cited_by_count":87},{"id":"1910.01663","title":"Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks","created":"2019-10-03","cited_by_count":87},{"id":"1901.01608","title":"Scaling description of generalization with number of parameters in deep learning","created":"2019-01-06","cited_by_count":83},{"id":"1603.04733","title":"Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors","created":"2016-03-15","cited_by_count":82},{"id":"1910.01619","title":"Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks","created":"2019-10-03","cited_by_count":79},{"id":"1704.08045","title":"The loss surface of deep and wide neural networks","created":"2017-04-26","cited_by_count":74},{"id":"2008.08601","title":"Neural Networks and Quantum Field Theory","created":"2020-08-19","cited_by_count":61},{"id":"2003.02237","title":"Neural Kernels Without Tangents","created":"2020-03-04","cited_by_count":56},{"id":"2006.13436","title":"Towards Understanding Hierarchical Learning: Benefits of Neural Representations","created":"2020-06-24","cited_by_count":46},{"id":"2005.08140","title":"Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes","created":"2020-05-17","cited_by_count":43},{"id":"1910.08013","title":"Why bigger is not always better: on finite and infinite neural networks","created":"2019-10-17","cited_by_count":41},{"id":"1602.04133","title":"Deep Gaussian Processes for Regression using Approximate Expectation Propagation","created":"2016-02-12","cited_by_count":39},{"id":"2010.01590","title":"Deep kernel processes","created":"2020-10-04","cited_by_count":34},{"id":"1402.5836","title":"Avoiding pathologies in very deep networks","created":"2014-02-24","cited_by_count":33},{"id":"1610.04386","title":"Random Feature Expansions for Deep Gaussian Processes","created":"2016-10-14","cited_by_count":32},{"id":"1806.05490","title":"Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo","created":"2018-06-14","cited_by_count":32},{"id":"2006.10541","title":"Exact posterior distributions of wide Bayesian neural networks","created":"2020-06-18","cited_by_count":30},{"id":"2105.04504","title":"Deep Neural Networks as Point Estimates for Deep Gaussian Processes","created":"2021-05-10","cited_by_count":26},{"id":"1810.03052","title":"Deep convolutional Gaussian processes","created":"2018-10-06","cited_by_count":21},{"id":"1902.05888","title":"Bayesian Image Classification with Deep Convolutional Gaussian Processes","created":"2019-02-15","cited_by_count":21},{"id":"1511.06455","title":"Variational Auto-encoded Deep Gaussian Processes","created":"2015-11-19","cited_by_count":20},{"id":"2001.00921","title":"Wide Neural Networks with Bottlenecks are Deep Gaussian Processes","created":"2020-01-03","cited_by_count":20},{"id":"2104.05674","title":"GPflux: A Library for Deep Gaussian Processes","created":"2021-04-12","cited_by_count":13},{"id":"1905.10963","title":"Interpretable deep Gaussian processes with moments","created":"2019-05-27","cited_by_count":8},{"id":"2003.05884","title":"Towards a General Theory of Infinite-Width Limits of Neural Classifiers","created":"2020-03-12","cited_by_count":7}],"next_cursor":null}