{"total":574,"rows":[{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649,"area":null},{"id":"2201.05624","title":"Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next","created":"2022-01-14","cited_by_count":608,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2302.07194","title":"Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data","created":"2023-02-14","cited_by_count":174,"area":"diffusion"},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166,"area":null},{"id":"2109.14545","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","created":"2021-09-29","cited_by_count":155,"area":null},{"id":"2305.19420","title":"What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization","created":"2023-05-30","cited_by_count":118,"area":null},{"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":"2205.06908","title":"Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds","created":"2022-05-13","cited_by_count":85,"area":null},{"id":"2402.15715","title":"Operator Learning: Algorithms and Analysis","created":"2024-02-24","cited_by_count":85,"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":"2312.14688","title":"A Mathematical Guide to Operator Learning","created":"2023-12-22","cited_by_count":76,"area":null},{"id":"2205.11393","title":"Generic bounds on the approximation error for physics-informed (and) operator learning","created":"2022-05-23","cited_by_count":65,"area":null},{"id":"2102.02981","title":"Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency","created":"2021-02-05","cited_by_count":56,"area":"offlinerl"},{"id":"2105.14835","title":"Towards Lower Bounds on the Depth of ReLU Neural Networks","created":"2021-05-31","cited_by_count":56,"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":"2210.08772","title":"Signal Processing for Implicit Neural Representations","created":"2022-10-17","cited_by_count":46,"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":"2412.02975","title":"Theoretical limitations of multi-layer Transformer","created":"2024-12-04","cited_by_count":45,"area":null},{"id":"2105.00266","title":"Data-driven discovery of Green's functions with human-understandable deep learning","created":"2021-05-01","cited_by_count":44,"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":"2408.01367","title":"Transformers are Universal In-context Learners","created":"2024-08-02","cited_by_count":43,"area":null},{"id":"2101.05390","title":"Universal Approximation Theorems for Differentiable Geometric Deep Learning","created":"2021-01-13","cited_by_count":41,"area":null},{"id":"2103.05632","title":"Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps","created":"2021-03-09","cited_by_count":41,"area":null},{"id":"2110.03187","title":"On the Optimal Memorization Power of ReLU Neural Networks","created":"2021-10-07","cited_by_count":40,"area":null},{"id":"2212.14424","title":"Normalizing flow neural networks by JKO scheme","created":"2022-12-29","cited_by_count":39,"area":null},{"id":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"area":null},{"id":"2309.11420","title":"Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models","created":"2023-09-20","cited_by_count":39,"area":"diffusion"},{"id":"2104.08135","title":"Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums","created":"2021-04-16","cited_by_count":37,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2408.12186","title":"Transformers are Minimax Optimal Nonparametric In-Context Learners","created":"2024-08-22","cited_by_count":37,"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":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36,"area":null},{"id":"2302.12553","title":"Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes","created":"2023-02-24","cited_by_count":36,"area":null},{"id":"2212.03130","title":"Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems","created":"2022-12-06","cited_by_count":34,"area":null},{"id":"2304.06879","title":"Performative Prediction with Neural Networks","created":"2023-04-14","cited_by_count":34,"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":"2109.02832","title":"Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks","created":"2021-09-07","cited_by_count":32,"area":null},{"id":"2406.13597","title":"GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks","created":"2024-06-19","cited_by_count":32,"area":null},{"id":"2210.04345","title":"LieGG: Studying Learned Lie Group Generators","created":"2022-10-09","cited_by_count":31,"area":null},{"id":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30,"area":null},{"id":"2210.01074","title":"Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2302.05933","title":"Generalization Ability of Wide Neural Networks on $\\mathbb{R}$","created":"2023-02-12","cited_by_count":30,"area":null},{"id":"2307.02301","title":"Sumformer: Universal Approximation for Efficient Transformers","created":"2023-07-05","cited_by_count":30,"area":null},{"id":"2403.02467","title":"Applied Causal Inference Powered by ML and AI","created":"2024-03-04","cited_by_count":30,"area":null},{"id":"2411.06646","title":"Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data","created":"2024-11-11","cited_by_count":30,"area":null},{"id":"2102.00491","title":"Learning elliptic partial differential equations with randomized linear algebra","created":"2021-01-31","cited_by_count":29,"area":null},{"id":"2206.09527","title":"Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2103.06183","title":"A Deep Learning approach to Reduced Order Modelling of Parameter Dependent Partial Differential Equations","created":"2021-03-10","cited_by_count":28,"area":null},{"id":"2102.13229","title":"Consistent Sparse Deep Learning: Theory and Computation","created":"2021-02-25","cited_by_count":27,"area":null},{"id":"2204.00997","title":"Bi-fidelity Modeling of Uncertain and Partially Unknown Systems using DeepONets","created":"2022-04-03","cited_by_count":27,"area":null},{"id":"2112.02548","title":"Generative Modeling of Turbulence","created":"2021-12-05","cited_by_count":26,"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":"2205.11404","title":"Variable-Input Deep Operator Networks","created":"2022-05-23","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":"2307.09835","title":"Deep Operator Network Approximation Rates for Lipschitz Operators","created":"2023-07-19","cited_by_count":24,"area":null},{"id":"2205.13863","title":"Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power","created":"2022-05-27","cited_by_count":23,"area":null},{"id":"2107.00896","title":"Theory of Deep Convolutional Neural Networks III: Approximating Radial Functions","created":"2021-07-02","cited_by_count":22,"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":"2210.13300","title":"Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis","created":"2022-10-24","cited_by_count":22,"area":null},{"id":"2309.01043","title":"Distribution learning via neural differential equations: a nonparametric statistical perspective","created":"2023-09-03","cited_by_count":22,"area":null},{"id":"2510.10981","title":"In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning","created":"2025-10-13","cited_by_count":22,"area":null},{"id":"2103.10293","title":"Neural tensor contractions and the expressive power of deep neural quantum states","created":"2021-03-18","cited_by_count":21,"area":null},{"id":"2108.00969","title":"Convergence rates of deep ReLU networks for multiclass classification","created":"2021-08-02","cited_by_count":21,"area":null},{"id":"2303.14878","title":"GPT-PINN: Generative Pre-Trained Physics-Informed Neural Networks toward non-intrusive Meta-learning of parametric PDEs","created":"2023-03-27","cited_by_count":20,"area":null},{"id":"2401.07187","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","created":"2024-01-14","cited_by_count":20,"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":"2103.02138","title":"Parametric Complexity Bounds for Approximating PDEs with Neural Networks","created":"2021-03-03","cited_by_count":19,"area":null},{"id":"2406.00134","title":"Anomaly Detection in Dynamic Graphs: A Comprehensive Survey","created":"2024-05-31","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":"2102.01621","title":"Depth separation beyond radial functions","created":"2021-02-02","cited_by_count":18,"area":null},{"id":"2205.11486","title":"Robust and Agnostic Learning of Conditional Distributional Treatment Effects","created":"2022-05-23","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":"2112.02393","title":"Optimization-Based Separations for Neural Networks","created":"2021-12-04","cited_by_count":17,"area":null},{"id":"2205.09459","title":"Neural Network Architecture Beyond Width and Depth","created":"2022-05-19","cited_by_count":17,"area":null},{"id":"2405.19883","title":"From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems","created":"2024-05-30","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":"2105.13011","title":"Neural Network Training Using $\\ell_1$-Regularization and Bi-fidelity Data","created":"2021-05-27","cited_by_count":16,"area":null},{"id":"2108.13054","title":"Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks","created":"2021-08-30","cited_by_count":16,"area":null},{"id":"2109.13359","title":"Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2111.14574","title":"On the rate of convergence of a classifier based on a Transformer encoder","created":"2021-11-29","cited_by_count":16,"area":null},{"id":"2307.12904","title":"Universal Approximation Theorem and error bounds for quantum neural networks and quantum reservoirs","created":"2023-07-24","cited_by_count":16,"area":null},{"id":"2107.12530","title":"Convergence of Deep ReLU Networks","created":"2021-07-27","cited_by_count":15,"area":null},{"id":"2107.13191","title":"Neural Network Approximation of Refinable Functions","created":"2021-07-28","cited_by_count":15,"area":null},{"id":"2109.00190","title":"Approximation Properties of Deep ReLU CNNs","created":"2021-09-01","cited_by_count":15,"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":"2204.01368","title":"Training Fully Connected Neural Networks is $\\exists\\mathbb{R}$-Complete","created":"2022-04-04","cited_by_count":15,"area":null},{"id":"2210.12101","title":"Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective","created":"2022-10-21","cited_by_count":15,"area":null},{"id":"2302.05851","title":"Deep Neural Networks for Nonparametric Interaction Models with Diverging Dimension","created":"2023-02-12","cited_by_count":15,"area":null},{"id":"2303.00579","title":"Are More Layers Beneficial to Graph Transformers?","created":"2023-03-01","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":"2310.19882","title":"Learning quantum states and unitaries of bounded gate complexity","created":"2023-10-30","cited_by_count":15,"area":null},{"id":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14,"area":null},{"id":"2402.00152","title":"Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss","created":"2024-01-31","cited_by_count":14,"area":null},{"id":"2410.00357","title":"Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study","created":"2024-10-01","cited_by_count":14,"area":null},{"id":"2109.13542","title":"Convergence of Deep Convolutional Neural Networks","created":"2021-09-28","cited_by_count":13,"area":null}],"next_cursor":"100"}