{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"1910.03193","title":"DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","created":"2019-10-08","cited_by_count":2018},{"id":"2011.00027","title":"The power of quantum neural networks","created":"2020-10-30","cited_by_count":379},{"id":"1703.02930","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","created":"2017-03-08","cited_by_count":311},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"1310.4375","title":"Fast Computation of Wasserstein Barycenters","created":"2013-10-16","cited_by_count":216},{"id":"1905.08539","title":"Universal Approximation with Deep Narrow Networks","created":"2019-05-21","cited_by_count":200},{"id":"1802.03620","title":"Optimal approximation of continuous functions by very deep ReLU networks","created":"2018-02-10","cited_by_count":166},{"id":"2102.03657","title":"Neural SDEs as Infinite-Dimensional GANs","created":"2021-02-06","cited_by_count":161},{"id":"1905.10403","title":"Neural Jump Stochastic Differential Equations","created":"2019-05-24","cited_by_count":150},{"id":"2009.08295","title":"Neural Rough Differential Equations for Long Time Series","created":"2020-09-17","cited_by_count":143},{"id":"1810.05749","title":"Graph HyperNetworks for Neural Architecture Search","created":"2018-10-12","cited_by_count":132},{"id":"1611.04231","title":"Identity Matters in Deep Learning","created":"2016-11-14","cited_by_count":109},{"id":"1802.03042","title":"Deep Hedging","created":"2018-02-08","cited_by_count":108},{"id":"1907.06673","title":"Quant GANs: Deep Generation of Financial Time Series","created":"2019-07-15","cited_by_count":108},{"id":"2006.08859","title":"Minimum Width for Universal Approximation","created":"2020-06-16","cited_by_count":94},{"id":"1906.09477","title":"The phase diagram of approximation rates for deep neural networks","created":"2019-06-22","cited_by_count":88},{"id":"1806.00797","title":"Echo state networks are universal","created":"2018-06-03","cited_by_count":87},{"id":"1702.05419","title":"A Random Matrix Approach to Neural Networks","created":"2017-02-17","cited_by_count":80},{"id":"1810.07770","title":"Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity","created":"2018-10-17","cited_by_count":78},{"id":"1808.08271","title":"An elementary introduction to information geometry","created":"2018-08-17","cited_by_count":76},{"id":"2010.14075","title":"Neural Network Approximation: Three Hidden Layers Are Enough","created":"2020-10-25","cited_by_count":63},{"id":"1509.07385","title":"Provable approximation properties for deep neural networks","created":"2015-09-24","cited_by_count":60},{"id":"1803.06917","title":"Universal features of price formation in financial markets: perspectives from Deep Learning","created":"2018-03-19","cited_by_count":60},{"id":"2111.01207","title":"Sig-Wasserstein GANs for Time Series Generation","created":"2021-11-01","cited_by_count":60},{"id":"1809.02362","title":"A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations","created":"2018-09-07","cited_by_count":55},{"id":"2201.04182","title":"HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning","created":"2022-01-11","cited_by_count":55},{"id":"1905.01208","title":"Approximation spaces of deep neural networks","created":"2019-05-03","cited_by_count":51},{"id":"1807.02621","title":"Reservoir Computing Universality With Stochastic Inputs","created":"2018-07-07","cited_by_count":48},{"id":"2201.00217","title":"Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces","created":"2022-01-01","cited_by_count":45},{"id":"2101.05390","title":"Universal Approximation Theorems for Differentiable Geometric Deep Learning","created":"2021-01-13","cited_by_count":41},{"id":"1712.00754","title":"Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems","created":"2017-12-03","cited_by_count":39},{"id":"1802.09128","title":"Averaging Stochastic Gradient Descent on Riemannian Manifolds","created":"2018-02-26","cited_by_count":39},{"id":"2102.10911","title":"Elementary superexpressive activations","created":"2021-02-22","cited_by_count":36},{"id":"2006.14498","title":"A Data-driven Market Simulator for Small Data Environments","created":"2020-06-21","cited_by_count":35},{"id":"2010.13363","title":"Provable Memorization via Deep Neural Networks using Sub-linear Parameters","created":"2020-10-26","cited_by_count":34},{"id":"2010.12047","title":"Fading memory echo state networks are universal","created":"2020-10-22","cited_by_count":32},{"id":"2110.03303","title":"Universal Approximation Under Constraints is Possible with Transformers","created":"2021-10-07","cited_by_count":32},{"id":"2005.02505","title":"A generative adversarial network approach to calibration of local stochastic volatility models","created":"2020-05-05","cited_by_count":29},{"id":"2006.02341","title":"Non-Euclidean Universal Approximation","created":"2020-06-03","cited_by_count":29},{"id":"2104.13669","title":"Optimal Stopping via Randomized Neural Networks","created":"2021-04-28","cited_by_count":28},{"id":"1802.05757","title":"Stochastic Wasserstein Barycenters","created":"2018-02-15","cited_by_count":25},{"id":"2010.14615","title":"Discrete-time signatures and randomness in reservoir computing","created":"2020-09-17","cited_by_count":23},{"id":"1901.01751","title":"Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination","created":"2019-01-07","cited_by_count":22},{"id":"1910.13886","title":"Risk bounds for reservoir computing","created":"2019-10-30","cited_by_count":22},{"id":"2007.04154","title":"Robust pricing and hedging via neural SDEs","created":"2020-07-08","cited_by_count":22},{"id":"1902.06094","title":"Differentiable reservoir computing","created":"2019-02-16","cited_by_count":20},{"id":"2105.11053","title":"Arbitrage-free neural-SDE market models","created":"2021-05-24","cited_by_count":19},{"id":"2112.06823","title":"Multi-Asset Spot and Option Market Simulation","created":"2021-12-13","cited_by_count":17},{"id":"2106.06682","title":"Solving PDEs on Unknown Manifolds with Machine Learning","created":"2021-06-12","cited_by_count":12},{"id":"2102.01962","title":"Deep Hedging under Rough Volatility","created":"2021-02-03","cited_by_count":10},{"id":"2012.06397","title":"Randomised Wasserstein Barycenter Computation: Resampling with Statistical Guarantees","created":"2020-12-11","cited_by_count":8},{"id":"2110.01127","title":"Deep Learning for Principal-Agent Mean Field Games","created":"2021-10-03","cited_by_count":5},{"id":"2010.15571","title":"Learning Sub-Patterns in Piecewise Continuous Functions","created":"2020-10-29","cited_by_count":4},{"id":"2105.02556","title":"Metric Entropy Limits on Recurrent Neural Network Learning of Linear Dynamical Systems","created":"2021-05-06","cited_by_count":4},{"id":"2105.07743","title":"Universal Regular Conditional Distributions","created":"2021-05-17","cited_by_count":4},{"id":"2201.04232","title":"Stochastic Gradient Descent for Barycenters in Wasserstein Space","created":"2022-01-11","cited_by_count":4},{"id":"2104.01437","title":"Monte Carlo Simulation of SDEs using GANs","created":"2021-04-03","cited_by_count":3},{"id":"2105.09917","title":"Neural networks with superexpressive activations and integer weights","created":"2021-05-20","cited_by_count":3},{"id":"2006.09455","title":"Consistent Recalibration Models and Deep Calibration","created":"2020-06-16","cited_by_count":1}],"next_cursor":null}