{"total":79,"rows":[{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343,"area":null},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102,"area":null},{"id":"2110.13040","title":"Neural Flows: Efficient Alternative to Neural ODEs","created":"2021-10-25","cited_by_count":101,"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":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55,"area":null},{"id":"2307.14023","title":"Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?","created":"2023-07-26","cited_by_count":47,"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":"2210.03008","title":"Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems","created":"2022-10-06","cited_by_count":21,"area":null},{"id":"2111.02922","title":"Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series","created":"2021-11-04","cited_by_count":16,"area":null},{"id":"2112.07096","title":"Learning High-Dimensional Parametric Maps via Reduced Basis Adaptive Residual Networks","created":"2021-12-14","cited_by_count":16,"area":null},{"id":"2204.06233","title":"Approximation of Lipschitz Functions using Deep Spline Neural Networks","created":"2022-04-13","cited_by_count":15,"area":null},{"id":"2407.12895","title":"A Survey on Universal Approximation Theorems","created":"2024-07-17","cited_by_count":15,"area":null},{"id":"2108.03603","title":"Understanding the computational demands underlying visual reasoning","created":"2021-08-08","cited_by_count":13,"area":null},{"id":"2203.11805","title":"Robust Classification using Contractive Hamiltonian Neural ODEs","created":"2022-03-22","cited_by_count":13,"area":null},{"id":"2211.13866","title":"Minimal Width for Universal Property of Deep RNN","created":"2022-11-25","cited_by_count":12,"area":null},{"id":"2401.02277","title":"Universal Approximation Theorem for Vector- and Hypercomplex-Valued Neural Networks","created":"2024-01-04","cited_by_count":11,"area":null},{"id":"2404.08921","title":"PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos","created":"2024-04-13","cited_by_count":10,"area":null},{"id":"2202.08070","title":"On Measuring Excess Capacity in Neural Networks","created":"2022-02-16","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2401.09902","title":"Interplay between depth and width for interpolation in neural ODEs","created":"2024-01-18","cited_by_count":9,"area":null},{"id":"2103.05793","title":"Universal Approximation of Residual Flows in Maximum Mean Discrepancy","created":"2021-03-10","cited_by_count":7,"area":null},{"id":"2110.02900","title":"Meta Internal Learning","created":"2021-10-06","cited_by_count":7,"area":null},{"id":"2206.09149","title":"Piecewise Linear Neural Networks and Deep Learning","created":"2022-06-18","cited_by_count":7,"area":null},{"id":"2207.07858","title":"The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network","created":"2022-07-16","cited_by_count":7,"area":null},{"id":"2112.07441","title":"An Interpretive Constrained Linear Model for ResNet and MgNet","created":"2021-12-14","cited_by_count":6,"area":null},{"id":"2301.07247","title":"Tailor: Altering Skip Connections for Resource-Efficient Inference","created":"2023-01-18","cited_by_count":6,"area":null},{"id":"2209.10909","title":"Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems","created":"2022-09-22","cited_by_count":4,"area":null},{"id":"2312.13807","title":"Cluster-based classification with neural ODEs via control","created":"2023-12-21","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":"2101.11487","title":"K\\\"ahler Geometry of Quiver Varieties and Machine Learning","created":"2021-01-27","cited_by_count":3,"area":null},{"id":"2312.12903","title":"A Minimal Control Family of Dynamical Systems for Universal Approximation","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2507.05164","title":"A Dynamical Systems Perspective on the Analysis of Neural Networks","created":"2025-07-07","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":"2108.01862","title":"Reconstructing a dynamical system and forecasting time series by self-consistent deep learning","created":"2021-08-04","cited_by_count":2,"area":null},{"id":"2111.12963","title":"Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2209.06910","title":"Modelling of physical systems with a Hopf bifurcation using mechanistic models and machine learning","created":"2022-09-07","cited_by_count":2,"area":null},{"id":"2303.12147","title":"Universal Approximation Property of Hamiltonian Deep Neural Networks","created":"2023-03-21","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},{"id":"2402.03629","title":"Disparate Impact on Group Accuracy of Linearization for Private Inference","created":"2024-02-06","cited_by_count":2,"area":null},{"id":"2405.13682","title":"Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2410.03292","title":"Demystifying the Token Dynamics of Deep Selective State Space Models","created":"2024-10-04","cited_by_count":2,"area":"ssm"},{"id":"2508.15394","title":"Hybrid Least Squares/Gradient Descent Methods for DeepONets","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2510.04138","title":"Efficient Manifold-Constrained Neural ODE for High-Dimensional Datasets","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2511.10841","title":"FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2512.03058","title":"Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2604.20219","title":"Layer-wise Geometric Approximation Rates for Deep Networks","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2107.01296","title":"Subspace Clustering Based Analysis of Neural Networks","created":"2021-07-02","cited_by_count":1,"area":null},{"id":"2205.06571","title":"Convergence Analysis of Deep Residual Networks","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2206.06885","title":"Neural interval-censored survival regression with feature selection","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2208.13305","title":"Neural Network Approximation of Continuous Functions in High Dimensions with Applications to Inverse Problems","created":"2022-08-28","cited_by_count":1,"area":null},{"id":"2211.13935","title":"LU decomposition and Toeplitz decomposition of a neural network","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2410.16709","title":"Universal approximation property of ODENet and ResNet with a single activation function","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2504.11433","title":"Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2506.24120","title":"Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2602.06471","title":"Revisiting the Shape Convention of Transformer Language Models","created":"2026-02-06","cited_by_count":1,"area":"inference"},{"id":"2605.05659","title":"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.19894","title":"Score Approximation for Diffusion Models on Arbitrary Low-Dimensional Structures","created":"2026-06-18","cited_by_count":1,"area":"diffusion"},{"id":"2101.01178","title":"Advances in Electron Microscopy with Deep Learning","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2104.01730","title":"Training Deep Neural Networks via Branch-and-Bound","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2105.09866","title":"Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field","created":"2021-05-11","cited_by_count":0,"area":null},{"id":"2209.03393","title":"The (Un)Scalability of Heuristic Approximators for NP-Hard Search Problems","created":"2022-09-07","cited_by_count":0,"area":null},{"id":"2210.12054","title":"Towards Global Neural Network Abstractions with Locally-Exact Reconstruction","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2212.05663","title":"On an Interpretation of ResNets via Solution Constructions","created":"2022-12-12","cited_by_count":0,"area":null},{"id":"2306.14650","title":"PhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2307.07726","title":"Towards Optimal Neural Networks: the Role of Sample Splitting in Hyperparameter Selection","created":"2023-07-15","cited_by_count":0,"area":null},{"id":"2309.06774","title":"Fundamental Limits of Deep Learning-Based Binary Classifiers Trained with Hinge Loss","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2505.24531","title":"Transformers Are Universally Consistent","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2510.03784","title":"Performance-Efficiency Tradeoffs in Transformers: An Approximation Theory Perspective","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2601.18264","title":"Neural Network Approximation: A View from Polytope Decomposition","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.28591","title":"Universal Approximation Constraints of Narrow ResNets: The Tunnel Effect","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.23705","title":"Can an MLP Absorb Its Own Skip Connection Exactly?","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2604.24154","title":"Progressive Approximation in Deep Residual Networks: Theory and Validation","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.01702","title":"Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.22557","title":"Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.04597","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.13574","title":"Approximation of solutions of parameter-dependent problems by residual neural networks","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.03626","title":"Residual neural networks overcome the curse of dimensionality for semilinear heat equations","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.01981","title":"Universal interpolation for deep residual self-attention networks","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.14385","title":"Deep learning from a control vantage point","created":"2026-10-09","cited_by_count":0,"area":"ssm"}],"next_cursor":null}