{"total":433,"rows":[{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649,"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":"2205.01445","title":"High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation","created":"2022-05-03","cited_by_count":150,"area":null},{"id":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143,"area":null},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2402.16991","title":"A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data","created":"2024-02-26","cited_by_count":93,"area":"diffusion"},{"id":"2402.15715","title":"Operator Learning: Algorithms and Analysis","created":"2024-02-24","cited_by_count":85,"area":null},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2404.07771","title":"An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization","created":"2024-04-11","cited_by_count":73,"area":"diffusion"},{"id":"2307.02129","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","created":"2023-07-05","cited_by_count":71,"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":"2304.06544","title":"DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos","created":"2023-04-13","cited_by_count":42,"area":null},{"id":"2109.08844","title":"Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks","created":"2021-09-18","cited_by_count":41,"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":"2106.05932","title":"Early-stopped neural networks are consistent","created":"2021-06-10","cited_by_count":34,"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":"2305.18699","title":"Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input","created":"2023-05-30","cited_by_count":32,"area":null},{"id":"2102.10032","title":"Approximation and Learning with Deep Convolutional Models: a Kernel Perspective","created":"2021-02-19","cited_by_count":31,"area":null},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","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":"2302.05933","title":"Generalization Ability of Wide Neural Networks on $\\mathbb{R}$","created":"2023-02-12","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":"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":"2102.13229","title":"Consistent Sparse Deep Learning: Theory and Computation","created":"2021-02-25","cited_by_count":27,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2410.13770","title":"Probing the Latent Hierarchical Structure of Data via Diffusion Models","created":"2024-10-17","cited_by_count":26,"area":"diffusion"},{"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":"2306.08321","title":"Nonparametric regression using over-parameterized shallow ReLU neural networks","created":"2023-06-14","cited_by_count":24,"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":"2309.01043","title":"Distribution learning via neural differential equations: a nonparametric statistical perspective","created":"2023-09-03","cited_by_count":22,"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":"2301.09554","title":"Deep Learning Meets Sparse Regularization: A Signal Processing Perspective","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2303.02186","title":"Causal Deep Learning","created":"2023-03-03","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":"2301.12227","title":"Deep Operator Learning Lessens the Curse of Dimensionality for PDEs","created":"2023-01-28","cited_by_count":18,"area":null},{"id":"2301.09517","title":"Sampling-based Nystr\\\"om Approximation and Kernel Quadrature","created":"2023-01-23","cited_by_count":17,"area":null},{"id":"2404.18444","title":"U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models","created":"2024-04-29","cited_by_count":17,"area":"diffusion"},{"id":"2106.12498","title":"Universal Consistency of Deep Convolutional Neural Networks","created":"2021-06-23","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":"2208.01003","title":"What Can Be Learnt With Wide Convolutional Neural Networks?","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2210.11530","title":"Theoretical analysis of deep neural networks for temporally dependent observations","created":"2022-10-20","cited_by_count":16,"area":null},{"id":"2310.03652","title":"Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics","created":"2023-10-05","cited_by_count":16,"area":null},{"id":"2103.04985","title":"Significance tests of feature relevance for a black-box learner","created":"2021-03-02","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":"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":"2108.11000","title":"Layer Adaptive Node Selection in Bayesian Neural Networks: Statistical Guarantees and Implementation Details","created":"2021-08-25","cited_by_count":14,"area":null},{"id":"2112.03657","title":"Understanding Square Loss in Training Overparametrized Neural Network Classifiers","created":"2021-12-07","cited_by_count":14,"area":null},{"id":"2209.01754","title":"Learning from a Biased Sample","created":"2022-09-05","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":"2507.02550","title":"Position: A Theory of Deep Learning Must Include Compositional Sparsity","created":"2025-07-03","cited_by_count":14,"area":null},{"id":"2102.00199","title":"Rates of convergence for density estimation with generative adversarial networks","created":"2021-01-30","cited_by_count":13,"area":null},{"id":"2111.08922","title":"Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification","created":"2021-11-17","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":"2306.11472","title":"Spatio-temporal DeepKriging for Interpolation and Probabilistic Forecasting","created":"2023-06-20","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":"2105.04046","title":"A likelihood approach to nonparametric estimation of a singular distribution using deep generative models","created":"2021-05-09","cited_by_count":12,"area":null},{"id":"2105.10475","title":"Generalization Error Bound for Hyperbolic Ordinal Embedding","created":"2021-05-21","cited_by_count":12,"area":null},{"id":"2210.16525","title":"Spectral Representation Learning for Conditional Moment Models","created":"2022-10-29","cited_by_count":12,"area":null},{"id":"2211.03860","title":"Automatic Change-Point Detection in Time Series via Deep Learning","created":"2022-11-07","cited_by_count":12,"area":null},{"id":"2402.01785","title":"DoubleMLDeep: Estimation of Causal Effects with Multimodal Data","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2207.02546","title":"Adaptive deep learning for nonlinear time series models","created":"2022-07-06","cited_by_count":11,"area":null},{"id":"2207.05683","title":"Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2209.07376","title":"Understanding Deep Neural Function Approximation in Reinforcement Learning via $\\epsilon$-Greedy Exploration","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2304.09157","title":"Neural networks for geospatial data","created":"2023-04-18","cited_by_count":11,"area":null},{"id":"2410.08026","title":"Generalization Bounds and Model Complexity for Kolmogorov-Arnold Networks","created":"2024-10-10","cited_by_count":11,"area":null},{"id":"2410.23440","title":"The Sample Complexity of Learning Lipschitz Operators with respect to Gaussian Measures","created":"2024-10-30","cited_by_count":11,"area":null},{"id":"2204.09664","title":"Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?","created":"2022-04-20","cited_by_count":10,"area":null},{"id":"2205.14818","title":"Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods","created":"2022-05-30","cited_by_count":10,"area":"distill"},{"id":"2210.04389","title":"DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning","created":"2022-10-10","cited_by_count":10,"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":"2406.03369","title":"Posterior and variational inference for deep neural networks with heavy-tailed weights","created":"2024-06-05","cited_by_count":10,"area":null},{"id":"2504.13336","title":"On the minimax optimality of Flow Matching through the connection to kernel density estimation","created":"2025-04-17","cited_by_count":10,"area":"diffusion"},{"id":"2109.03992","title":"Stationary Density Estimation of It\\^o Diffusions Using Deep Learning","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2112.12555","title":"Optimal learning of high-dimensional classification problems using deep neural networks","created":"2021-12-23","cited_by_count":9,"area":null},{"id":"2210.14184","title":"Learning Ability of Interpolating Deep Convolutional Neural Networks","created":"2022-10-25","cited_by_count":9,"area":null},{"id":"2212.05427","title":"Statistical guarantees for sparse deep learning","created":"2022-12-11","cited_by_count":9,"area":null},{"id":"2302.07503","title":"Excess risk bound for deep learning under weak dependence","created":"2023-02-15","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":"2305.14765","title":"Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2506.07958","title":"Neural Tangent Kernel Analysis to Probe Convergence in Physics-informed Neural Solvers: PIKANs vs. PINNs","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2202.10887","title":"Policy Evaluation for Temporal and/or Spatial Dependent Experiments","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2303.01406","title":"Sparse-penalized deep neural networks estimator under weak dependence","created":"2023-03-02","cited_by_count":8,"area":null},{"id":"2305.10015","title":"Utility Theory of Synthetic Data Generation","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2306.16549","title":"UTOPIA: Universally Trainable Optimal Prediction Intervals Aggregation","created":"2023-06-28","cited_by_count":8,"area":null},{"id":"2404.18769","title":"Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2406.11110","title":"How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD","created":"2024-06-17","cited_by_count":8,"area":null},{"id":"2410.11474","title":"How Transformers Get Rich: Approximation and Dynamics Analysis","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2411.13443","title":"Nonlinear Assimilation via Score-based Sequential Langevin Sampling","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2103.00542","title":"Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on H\\\"older Class","created":"2021-02-28","cited_by_count":7,"area":null},{"id":"2108.01312","title":"Learning Causal Models from Conditional Moment Restrictions by Importance Weighting","created":"2021-08-03","cited_by_count":7,"area":null},{"id":"2110.00653","title":"Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration","created":"2021-10-01","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":"2206.00241","title":"Asymptotic Properties for Bayesian Neural Network in Besov Space","created":"2022-06-01","cited_by_count":7,"area":null}],"next_cursor":"100"}