{"total":135,"rows":[{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233,"area":null},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221,"area":null},{"id":"2107.07871","title":"Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations","created":"2021-07-16","cited_by_count":145,"area":null},{"id":"2308.08468","title":"An Expert's Guide to Training Physics-informed Neural Networks","created":"2023-08-16","cited_by_count":126,"area":null},{"id":"2201.07395","title":"Overview frequency principle/spectral bias in deep learning","created":"2022-01-19","cited_by_count":69,"area":null},{"id":"2108.10573","title":"The staircase property: How hierarchical structure can guide deep learning","created":"2021-08-24","cited_by_count":62,"area":null},{"id":"2111.02447","title":"On the Frequency Bias of Generative Models","created":"2021-11-03","cited_by_count":60,"area":null},{"id":"2104.09125","title":"SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization","created":"2021-04-19","cited_by_count":59,"area":null},{"id":"2409.10594","title":"Kolmogorov-Arnold Transformer","created":"2024-09-16","cited_by_count":56,"area":null},{"id":"2210.10890","title":"Mitigating spectral bias for the multiscale operator learning","created":"2022-10-19","cited_by_count":44,"area":null},{"id":"2101.08366","title":"Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEs","created":"2021-01-20","cited_by_count":43,"area":null},{"id":"2110.02424","title":"Spectral Bias in Practice: The Role of Function Frequency in Generalization","created":"2021-10-06","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":"2401.07402","title":"Improved Implicit Neural Representation with Fourier Reparameterized Training","created":"2024-01-15","cited_by_count":36,"area":null},{"id":"2305.02657","title":"On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains","created":"2023-05-04","cited_by_count":31,"area":null},{"id":"2211.07871","title":"DINER: Disorder-Invariant Implicit Neural Representation","created":"2022-11-15","cited_by_count":30,"area":null},{"id":"2308.12553","title":"Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy","created":"2023-08-24","cited_by_count":30,"area":null},{"id":"2304.00837","title":"Disorder-invariant Implicit Neural Representation","created":"2023-04-03","cited_by_count":27,"area":null},{"id":"2312.15995","title":"Generalization in Kernel Regression Under Realistic Assumptions","created":"2023-12-26","cited_by_count":27,"area":null},{"id":"2105.04504","title":"Deep Neural Networks as Point Estimates for Deep Gaussian Processes","created":"2021-05-10","cited_by_count":26,"area":null},{"id":"2302.00457","title":"Simplicity Bias in 1-Hidden Layer Neural Networks","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2207.05952","title":"Implicit regularization of dropout","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2211.15188","title":"Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2206.14373","title":"Theoretical Perspectives on Deep Learning Methods in Inverse Problems","created":"2022-06-29","cited_by_count":22,"area":null},{"id":"2211.07844","title":"Characterizing the Spectrum of the NTK via a Power Series Expansion","created":"2022-11-15","cited_by_count":22,"area":null},{"id":"2104.03093","title":"Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks","created":"2021-04-07","cited_by_count":21,"area":null},{"id":"2109.06099","title":"Uniform Generalization Bounds for Overparameterized Neural Networks","created":"2021-09-13","cited_by_count":21,"area":null},{"id":"2206.10121","title":"Finite Expression Method for Solving High-Dimensional Partial Differential Equations","created":"2022-06-21","cited_by_count":21,"area":null},{"id":"2210.05577","title":"What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?","created":"2022-10-11","cited_by_count":21,"area":null},{"id":"2202.13473","title":"The Spectral Bias of Polynomial Neural Networks","created":"2022-02-27","cited_by_count":19,"area":null},{"id":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2112.03257","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","created":"2021-12-06","cited_by_count":17,"area":null},{"id":"2410.02035","title":"Tuning Frequency Bias of State Space Models","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2103.02695","title":"Shift Invariance Can Reduce Adversarial Robustness","created":"2021-03-03","cited_by_count":16,"area":null},{"id":"2203.09255","title":"On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2305.12133","title":"Loss Spike in Training Neural Networks","created":"2023-05-20","cited_by_count":16,"area":null},{"id":"2110.12231","title":"Learning curves for Gaussian process regression with power-law priors and targets","created":"2021-10-23","cited_by_count":15,"area":null},{"id":"2312.14050","title":"Machine learning and domain decomposition methods -- a survey","created":"2023-12-21","cited_by_count":14,"area":null},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2410.05050","title":"FreSh: Frequency Shifting for Accelerated Neural Representation Learning","created":"2024-10-07","cited_by_count":14,"area":null},{"id":"2410.16105","title":"Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning","created":"2024-10-21","cited_by_count":14,"area":null},{"id":"2103.05243","title":"On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2310.14184","title":"Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis","created":"2023-10-22","cited_by_count":13,"area":null},{"id":"2402.05173","title":"Towards Understanding Inductive Bias in Transformers: A View From Infinity","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2405.14630","title":"Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2206.02927","title":"Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime","created":"2022-06-06","cited_by_count":11,"area":null},{"id":"2401.08309","title":"Anchor function: a type of benchmark functions for studying language models","created":"2024-01-16","cited_by_count":11,"area":null},{"id":"2410.04779","title":"Fast Training of Sinusoidal Neural Fields via Scaling Initialization","created":"2024-10-07","cited_by_count":11,"area":null},{"id":"2103.11093","title":"Exploring The Effect of High-frequency Components in GANs Training","created":"2021-03-20","cited_by_count":10,"area":null},{"id":"2105.05553","title":"Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks","created":"2021-05-12","cited_by_count":10,"area":null},{"id":"2112.06660","title":"Subspace Decomposition based DNN algorithm for elliptic type multi-scale PDEs","created":"2021-12-10","cited_by_count":10,"area":null},{"id":"2305.09779","title":"A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks","created":"2023-05-16","cited_by_count":10,"area":null},{"id":"2201.04738","title":"Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks","created":"2022-01-12","cited_by_count":9,"area":null},{"id":"2307.14531","title":"Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum","created":"2023-07-26","cited_by_count":9,"area":null},{"id":"2501.01681","title":"SNeRV: Spectra-preserving Neural Representation for Video","created":"2025-01-03","cited_by_count":9,"area":null},{"id":"2105.03491","title":"Uniform Convergence, Adversarial Spheres and a Simple Remedy","created":"2021-05-07","cited_by_count":8,"area":null},{"id":"2307.14363","title":"Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields","created":"2023-07-24","cited_by_count":8,"area":null},{"id":"2310.00987","title":"A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2410.06300","title":"SHAP values via sparse Fourier representation","created":"2024-10-08","cited_by_count":8,"area":null},{"id":"2410.13271","title":"Inductive Gradient Adjustment For Spectral Bias In Implicit Neural Representations","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2505.09022","title":"Block-Biased Mamba for Long-Range Sequence Processing","created":"2025-05-13","cited_by_count":8,"area":"ssm"},{"id":"2110.00494","title":"Probabilistic Robust Autoencoders for Outlier Detection","created":"2021-10-01","cited_by_count":7,"area":null},{"id":"2201.01386","title":"Deep learning for location based beamforming with NLOS channels","created":"2021-12-29","cited_by_count":7,"area":null},{"id":"2303.02034","title":"Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies","created":"2023-03-03","cited_by_count":7,"area":null},{"id":"2305.14477","title":"A Block-Coordinate Approach of Multi-level Optimization with an Application to Physics-Informed Neural Networks","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2311.17094","title":"In Search of a Data Transformation That Accelerates Neural Field Training","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2412.03077","title":"RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos","created":"2024-12-04","cited_by_count":7,"area":null},{"id":"2211.14503","title":"Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth","created":"2022-11-26","cited_by_count":6,"area":null},{"id":"2305.08813","title":"Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks","created":"2023-05-15","cited_by_count":6,"area":null},{"id":"2308.09519","title":"Leveraging Intrinsic Properties for Non-Rigid Garment Alignment","created":"2023-08-18","cited_by_count":6,"area":null},{"id":"2501.00288","title":"Solving Partial Differential Equations with Random Feature Models","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2209.09658","title":"Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2506.22555","title":"Spectral Bias in Variational Quantum Machine Learning","created":"2025-06-27","cited_by_count":5,"area":null},{"id":"2101.00747","title":"Frequency Principle in Deep Learning Beyond Gradient-descent-based Training","created":"2021-01-04","cited_by_count":4,"area":null},{"id":"2105.11675","title":"An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2205.12642","title":"On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2206.14862","title":"Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks","created":"2022-06-29","cited_by_count":4,"area":null},{"id":"2302.11883","title":"PIFON-EPT: MR-Based Electrical Property Tomography Using Physics-Informed Fourier Networks","created":"2023-02-23","cited_by_count":4,"area":null},{"id":"2404.13182","title":"Spectral Convolutional Conditional Neural Processes","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2405.14957","title":"Understanding the dynamics of the frequency bias in neural networks","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2406.02105","title":"Can Kernel Methods Explain How the Data Affects Neural Collapse?","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2410.06308","title":"Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2503.11029","title":"Neural Tangent Kernel of Neural Networks with Loss Informed by Differential Operators","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2301.05816","title":"Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics","created":"2023-01-14","cited_by_count":3,"area":null},{"id":"2404.09738","title":"AMPCliff: quantitative definition and benchmarking of activity cliffs in antimicrobial peptides","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2405.17479","title":"A rationale from frequency perspective for grokking in training neural network","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2406.02663","title":"Demystifying Spectral Bias on Real-World Data","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2408.00775","title":"Dilated convolution neural operator for multiscale partial differential equations","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2501.14980","title":"A Deep State Space Model for Rainfall-Runoff Simulations","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2504.13412","title":"How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2506.22429","title":"Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks","created":"2025-06-27","cited_by_count":3,"area":null},{"id":"2511.15779","title":"SURFing to the Fundamental Limit of Jet Tagging","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2212.00270","title":"On the Compatibility between Neural Networks and Partial Differential Equations for Physics-informed Learning","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2303.08455","title":"On the uncertainty analysis of the data-enabled physics-informed neural network for solving neutron diffusion eigenvalue problem","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2405.04536","title":"When Training-Free NAS Meets Vision Transformer: A Neural Tangent Kernel Perspective","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2410.12025","title":"Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2410.21645","title":"Predicting the Encoding Error of SIRENs","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2502.00280","title":"On the study of frequency control and spectral bias in Wavelet-Based Kolmogorov Arnold networks: A path to physics-informed KANs","created":"2025-02-01","cited_by_count":2,"area":null}],"next_cursor":"100"}