{"total":68,"rows":[{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2006.13198","title":"Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks","created":"2020-06-23","cited_by_count":166,"area":"alignment"},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154,"area":null},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"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":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51,"area":"offlinerl"},{"id":"2403.02241","title":"Neural Redshift: Random Networks are not Random Functions","created":"2024-03-04","cited_by_count":43,"area":null},{"id":"2302.02774","title":"The SSL Interplay: Augmentations, Inductive Bias, and Generalization","created":"2023-02-06","cited_by_count":40,"area":null},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"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":"2208.04924","title":"On the Activation Function Dependence of the Spectral Bias of Neural Networks","created":"2022-08-09","cited_by_count":28,"area":null},{"id":"2304.06670","title":"Deep neural networks have an inbuilt Occam's razor","created":"2023-04-13","cited_by_count":28,"area":null},{"id":"2312.15995","title":"Generalization in Kernel Regression Under Realistic Assumptions","created":"2023-12-26","cited_by_count":27,"area":null},{"id":"2110.03922","title":"The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks","created":"2021-10-08","cited_by_count":26,"area":null},{"id":"2105.14301","title":"A Theory of Neural Tangent Kernel Alignment and Its Influence on Training","created":"2021-05-29","cited_by_count":25,"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":"2106.05566","title":"A Neural Tangent Kernel Perspective of GANs","created":"2021-06-10","cited_by_count":21,"area":null},{"id":"2302.00453","title":"Width and Depth Limits Commute in Residual Networks","created":"2023-02-01","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":"2112.05611","title":"Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networks","created":"2021-12-10","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":"2505.17495","title":"ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs","created":"2025-05-23","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":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2103.06219","title":"Why flatness does and does not correlate with generalization for deep neural networks","created":"2021-03-10","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":"2106.03186","title":"Reverse Engineering the Neural Tangent Kernel","created":"2021-06-06","cited_by_count":12,"area":null},{"id":"2502.13870","title":"SPEX: Scaling Feature Interaction Explanations for LLMs","created":"2025-02-19","cited_by_count":12,"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":"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":"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":"2410.06300","title":"SHAP values via sparse Fourier representation","created":"2024-10-08","cited_by_count":8,"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":"2410.21273","title":"On Inductive Biases That Enable Generalization of Diffusion Transformers","created":"2024-10-28","cited_by_count":7,"area":"diffusion"},{"id":"2207.04612","title":"Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm","created":"2022-07-11","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":"2305.09145","title":"Deep ReLU Networks Have Surprisingly Simple Polytopes","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2306.05850","title":"Deterministic equivalent of the Conjugate Kernel matrix associated to Artificial Neural Networks","created":"2023-06-09","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":"2105.00507","title":"Universal scaling laws in the gradient descent training of neural networks","created":"2021-05-02","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":"2405.14957","title":"Understanding the dynamics of the frequency bias in neural networks","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2111.03972","title":"Understanding Layer-wise Contributions in Deep Neural Networks through Spectral Analysis","created":"2021-11-06","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":"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":"2107.09139","title":"Constrained Policy Gradient Method for Safe and Fast Reinforcement Learning: a Neural Tangent Kernel Based Approach","created":"2021-07-19","cited_by_count":2,"area":null},{"id":"2410.04228","title":"SGD with memory: fundamental properties and stochastic acceleration","created":"2024-10-05","cited_by_count":2,"area":null},{"id":"2507.05035","title":"Beyond Scaling Curves: Internal Dynamics of Neural Networks Through the NTK Lens","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2210.02604","title":"Spectral Regularization Allows Data-frugal Learning over Combinatorial Spaces","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2211.01236","title":"Isometric Representations in Neural Networks Improve Robustness","created":"2022-11-02","cited_by_count":1,"area":null},{"id":"2211.09184","title":"An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks","created":"2022-11-16","cited_by_count":1,"area":null},{"id":"2310.01683","title":"Commutative Width and Depth Scaling in Deep Neural Networks","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2410.08311","title":"Correspondence of NNGP Kernel and the Matern Kernel","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2505.24060","title":"Characterising the Inductive Biases of Neural Networks on Boolean Data","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2508.21040","title":"FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2201.09223","title":"A Generalized Weighted Optimization Method for Computational Learning and Inversion","created":"2022-01-23","cited_by_count":0,"area":null},{"id":"2401.00593","title":"Simplicity bias, algorithmic probability, and the random logistic map","created":"2023-12-31","cited_by_count":0,"area":null},{"id":"2406.09194","title":"Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2410.10182","title":"Hamiltonian Neural Networks for Robust Out-of-Time Credit Scoring","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2512.12898","title":"Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.03066","title":"Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.08287","title":"Noise Stability of Transformer Models","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.08695","title":"Trapped by simplicity: When Transformers fail to learn from noisy features","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2607.06949","title":"SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}