{"total":161,"rows":[{"id":"2103.00502","title":"Optimal Approximation Rate of ReLU Networks in terms of Width and Depth","created":"2021-02-28","cited_by_count":96,"area":null},{"id":"2104.08938","title":"On the approximation of functions by tanh neural networks","created":"2021-04-18","cited_by_count":81,"area":null},{"id":"2211.14400","title":"Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces","created":"2022-11-25","cited_by_count":51,"area":null},{"id":"2103.09959","title":"Evolutional Deep Neural Network","created":"2021-03-18","cited_by_count":50,"area":null},{"id":"2201.00217","title":"Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces","created":"2022-01-01","cited_by_count":45,"area":null},{"id":"2107.01562","title":"Random Neural Networks in the Infinite Width Limit as Gaussian Processes","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2303.16317","title":"Operator learning with PCA-Net: upper and lower complexity bounds","created":"2023-03-28","cited_by_count":44,"area":null},{"id":"2107.02397","title":"Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons","created":"2021-07-06","cited_by_count":41,"area":null},{"id":"2410.01803","title":"On the expressiveness and spectral bias of KANs","created":"2024-10-02","cited_by_count":37,"area":null},{"id":"2105.13010","title":"An error analysis of generative adversarial networks for learning distributions","created":"2021-05-27","cited_by_count":36,"area":null},{"id":"2410.01405","title":"On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding","created":"2024-10-02","cited_by_count":36,"area":null},{"id":"2205.01510","title":"ExSpliNet: An interpretable and expressive spline-based neural network","created":"2022-05-03","cited_by_count":33,"area":null},{"id":"2307.06555","title":"Deep Network Approximation: Beyond ReLU to Diverse Activation Functions","created":"2023-07-13","cited_by_count":33,"area":null},{"id":"2104.02746","title":"Proof of the Theory-to-Practice Gap in Deep Learning via Sampling Complexity bounds for Neural Network Approximation Spaces","created":"2021-04-06","cited_by_count":30,"area":null},{"id":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30,"area":null},{"id":"2106.07539","title":"On the Representation of Solutions to Elliptic PDEs in Barron Spaces","created":"2021-06-14","cited_by_count":25,"area":null},{"id":"2203.10418","title":"How do noise tails impact on deep ReLU networks?","created":"2022-03-20","cited_by_count":25,"area":null},{"id":"2112.10039","title":"Wasserstein Generative Learning of Conditional Distribution","created":"2021-12-19","cited_by_count":24,"area":null},{"id":"2201.09418","title":"Approximation bounds for norm constrained neural networks with applications to regression and GANs","created":"2022-01-24","cited_by_count":22,"area":null},{"id":"2201.13094","title":"Designing Universal Causal Deep Learning Models: The Geometric (Hyper)Transformer","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2101.04844","title":"Reproducing Activation Function for Deep Learning","created":"2021-01-13","cited_by_count":19,"area":null},{"id":"2101.12353","title":"On the capacity of deep generative networks for approximating distributions","created":"2021-01-29","cited_by_count":19,"area":null},{"id":"2101.01708","title":"A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations","created":"2021-01-05","cited_by_count":18,"area":null},{"id":"2301.12227","title":"Deep Operator Learning Lessens the Curse of Dimensionality for PDEs","created":"2023-01-28","cited_by_count":18,"area":null},{"id":"2309.10402","title":"Minimum width for universal approximation using ReLU networks on compact domain","created":"2023-09-19","cited_by_count":18,"area":null},{"id":"2205.09459","title":"Neural Network Architecture Beyond Width and Depth","created":"2022-05-19","cited_by_count":17,"area":null},{"id":"2101.11256","title":"Partition of unity networks: deep hp-approximation","created":"2021-01-27","cited_by_count":16,"area":null},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2404.09101","title":"Mixtures of Neural Operators Reduce Active Complexity in Operator Learning","created":"2024-04-13","cited_by_count":16,"area":null},{"id":"2203.05142","title":"IAE-Net: Integral Autoencoders for Discretization-Invariant Learning","created":"2022-03-10","cited_by_count":15,"area":null},{"id":"2304.01561","title":"Optimal rates of approximation by shallow ReLU$^k$ neural networks and applications to nonparametric regression","created":"2023-04-04","cited_by_count":15,"area":null},{"id":"2110.04227","title":"Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows","created":"2021-10-08","cited_by_count":13,"area":null},{"id":"2111.11153","title":"Plant 'n' Seek: Can You Find the Winning Ticket?","created":"2021-11-22","cited_by_count":13,"area":null},{"id":"2210.08367","title":"Active Learning with Neural Networks: Insights from Nonparametric Statistics","created":"2022-10-15","cited_by_count":13,"area":null},{"id":"2308.05509","title":"On the Optimal Expressive Power of ReLU DNNs and Its Application in Approximation with Kolmogorov Superposition Theorem","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2409.00901","title":"On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks","created":"2024-09-02","cited_by_count":13,"area":null},{"id":"2106.06682","title":"Solving PDEs on Unknown Manifolds with Machine Learning","created":"2021-06-12","cited_by_count":12,"area":null},{"id":"2111.07964","title":"Deep Network Approximation in Terms of Intrinsic Parameters","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2206.04360","title":"A general approximation lower bound in $L^p$ norm, with applications to feed-forward neural networks","created":"2022-06-09","cited_by_count":12,"area":null},{"id":"2310.07528","title":"Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2403.16459","title":"On the rates of convergence for learning with convolutional neural networks","created":"2024-03-25","cited_by_count":10,"area":null},{"id":"2110.04600","title":"A Review of Physics-based Machine Learning in Civil Engineering","created":"2021-10-09","cited_by_count":9,"area":null},{"id":"2208.08707","title":"Deep Neural Network Approximation of Invariant Functions through Dynamical Systems","created":"2022-08-18","cited_by_count":9,"area":null},{"id":"2305.00608","title":"Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression","created":"2023-05-01","cited_by_count":9,"area":null},{"id":"2407.09505","title":"1-Lipschitz Neural Distance Fields","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2304.04443","title":"Approximation of Nonlinear Functionals Using Deep ReLU Networks","created":"2023-04-10","cited_by_count":8,"area":null},{"id":"2312.14276","title":"Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions","created":"2023-12-21","cited_by_count":8,"area":null},{"id":"2102.00314","title":"Size and Depth Separation in Approximating Benign Functions with Neural Networks","created":"2021-01-30","cited_by_count":7,"area":null},{"id":"2205.07764","title":"On the inability of Gaussian process regression to optimally learn compositional functions","created":"2022-05-16","cited_by_count":7,"area":null},{"id":"2209.08399","title":"Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$","created":"2022-09-17","cited_by_count":7,"area":null},{"id":"2211.14047","title":"On the Universal Approximation Property of Deep Fully Convolutional Neural Networks","created":"2022-11-25","cited_by_count":7,"area":null},{"id":"2310.18612","title":"Efficient kernel surrogates for neural network-based regression","created":"2023-10-28","cited_by_count":7,"area":null},{"id":"2401.02890","title":"Nonlinear functional regression by functional deep neural network with kernel embedding","created":"2024-01-05","cited_by_count":7,"area":null},{"id":"2404.03761","title":"Learning smooth functions in high dimensions: from sparse polynomials to deep neural networks","created":"2024-04-04","cited_by_count":7,"area":null},{"id":"2407.09580","title":"Don't Fear Peculiar Activation Functions: EUAF and Beyond","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2505.12003","title":"Approximation theory for 1-Lipschitz ResNets","created":"2025-05-17","cited_by_count":7,"area":null},{"id":"2204.11231","title":"Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?","created":"2022-04-24","cited_by_count":6,"area":null},{"id":"2208.12190","title":"CAS4DL: Christoffel Adaptive Sampling for function approximation via Deep Learning","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2212.01314","title":"On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds","created":"2022-12-02","cited_by_count":6,"area":null},{"id":"2301.12353","title":"On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network","created":"2023-01-29","cited_by_count":6,"area":null},{"id":"2303.03918","title":"Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2401.15121","title":"Expressive Power of ReLU and Step Networks under Floating-Point Operations","created":"2024-01-26","cited_by_count":5,"area":null},{"id":"2405.08276","title":"Scalable Subsampling Inference for Deep Neural Networks","created":"2024-05-14","cited_by_count":5,"area":null},{"id":"2405.15673","title":"Consistency of Neural Causal Partial Identification","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2504.13558","title":"Transformers Can Overcome the Curse of Dimensionality: A Theoretical Study from an Approximation Perspective","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2101.07023","title":"Deep neural network surrogates for non-smooth quantities of interest in shape uncertainty quantification","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2105.00292","title":"Non-asymptotic Excess Risk Bounds for Classification with Deep Convolutional Neural Networks","created":"2021-05-01","cited_by_count":4,"area":null},{"id":"2105.06849","title":"Sparsity-Probe: Analysis tool for Deep Learning Models","created":"2021-05-14","cited_by_count":4,"area":null},{"id":"2212.02223","title":"Limitations on approximation by deep and shallow neural networks","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2305.11417","title":"Exploring the Complexity of Deep Neural Networks through Functional Equivalence","created":"2023-05-19","cited_by_count":4,"area":null},{"id":"2308.03230","title":"Tractability of approximation by general shallow networks","created":"2023-08-07","cited_by_count":4,"area":null},{"id":"2310.19603","title":"Transformers Can Solve Non-Linear and Non-Markovian Filtering Problems in Continuous Time For Conditionally Gaussian Signals","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2409.05577","title":"Approximation Bounds for Recurrent Neural Networks with Application to Regression","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2410.01047","title":"Spherical Analysis of Learning Nonlinear Functionals","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2411.06241","title":"Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability","created":"2024-11-09","cited_by_count":4,"area":null},{"id":"2502.18959","title":"Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2504.15110","title":"Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2506.02293","title":"On Universality Classes of Equivariant Networks","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2111.07080","title":"Deep Learning in High Dimension: Neural Network Approximation of Analytic Functions in $L^2(\\mathbb{R}^d,\\gamma_d)$","created":"2021-11-13","cited_by_count":3,"area":null},{"id":"2207.10442","title":"Estimation of Non-Crossing Quantile Regression Process with Deep ReQU Neural Networks","created":"2022-07-21","cited_by_count":3,"area":null},{"id":"2209.03450","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2211.08900","title":"Convergence analysis of unsupervised Legendre-Galerkin neural networks for linear second-order elliptic PDEs","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2302.00834","title":"Sharp Lower Bounds on Interpolation by Deep ReLU Neural Networks at Irregularly Spaced Data","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2305.16910","title":"Universal approximation with complex-valued deep narrow neural networks","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2402.08808","title":"Depth Separation in Norm-Bounded Infinite-Width Neural Networks","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2405.20094","title":"Low-dimensional approximations of the conditional law of Volterra processes: a non-positive curvature approach","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2407.00765","title":"Structured and Balanced Multi-Component and Multi-Layer Neural Networks","created":"2024-06-30","cited_by_count":3,"area":null},{"id":"2503.04263","title":"Bi-Lipschitz Ansatz for Anti-Symmetric Functions","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2504.07371","title":"Minimum width for universal approximation using squashable activation functions","created":"2025-04-10","cited_by_count":3,"area":null},{"id":"2505.01557","title":"Contextures: Representations from Contexts","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2507.10345","title":"Some Super-approximation Rates of ReLU Neural Networks for Korobov Functions","created":"2025-07-14","cited_by_count":3,"area":null},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2510.15814","title":"On Universality of Deep Equivariant Networks","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2605.31152","title":"Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2210.00805","title":"Limitations of neural network training due to numerical instability of backpropagation","created":"2022-10-03","cited_by_count":2,"area":null},{"id":"2309.00771","title":"Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Models","created":"2023-09-02","cited_by_count":2,"area":null},{"id":"2309.04860","title":"Approximation Results for Gradient Descent trained Neural Networks","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2310.00729","title":"Spectral Neural Networks: Approximation Theory and Optimization Landscape","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2310.03529","title":"Deep Ridgelet Transform: Voice with Koopman Operator Proves Universality of Formal Deep Networks","created":"2023-10-05","cited_by_count":2,"area":null}],"next_cursor":"100"}