{"total":85,"rows":[{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167,"area":null},{"id":"2106.06610","title":"Scalars are universal: Equivariant machine learning, structured like classical physics","created":"2021-06-11","cited_by_count":127,"area":null},{"id":"2112.09992","title":"Weisfeiler and Leman go Machine Learning: The Story so far","created":"2021-12-18","cited_by_count":122,"area":null},{"id":"2305.17592","title":"Approximation-Generalization Trade-offs under (Approximate) Group Equivariance","created":"2023-05-27","cited_by_count":46,"area":null},{"id":"2204.10425","title":"Spectrum of inner-product kernel matrices in the polynomial regime and multiple descent phenomenon in kernel ridge regression","created":"2022-04-21","cited_by_count":45,"area":null},{"id":"2402.16077","title":"Equivariant Frames and the Impossibility of Continuous Canonicalization","created":"2024-02-25","cited_by_count":43,"area":null},{"id":"2205.06109","title":"Equivariant quantum circuits for learning on weighted graphs","created":"2022-05-12","cited_by_count":41,"area":null},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"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":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2104.04244","title":"How rotational invariance of common kernels prevents generalization in high dimensions","created":"2021-04-09","cited_by_count":32,"area":null},{"id":"2106.02346","title":"Provably Strict Generalisation Benefit for Invariance in Kernel Methods","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30,"area":null},{"id":"2202.00565","title":"Data-driven emergence of convolutional structure in neural networks","created":"2022-02-01","cited_by_count":29,"area":null},{"id":"2202.12230","title":"Sample Efficiency of Data Augmentation Consistency Regularization","created":"2022-02-24","cited_by_count":28,"area":null},{"id":"2303.14269","title":"The Exact Sample Complexity Gain from Invariances for Kernel Regression","created":"2023-03-24","cited_by_count":28,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2210.05021","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2410.02698","title":"Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups","created":"2024-10-03","cited_by_count":24,"area":null},{"id":"2111.07167","title":"The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods","created":"2021-11-13","cited_by_count":22,"area":null},{"id":"2111.08308","title":"Learning with convolution and pooling operations in kernel methods","created":"2021-11-16","cited_by_count":21,"area":null},{"id":"2202.07552","title":"A Theory of PAC Learnability under Transformation Invariances","created":"2022-02-15","cited_by_count":21,"area":null},{"id":"2305.08404","title":"Theoretical Analysis of Inductive Biases in Deep Convolutional Networks","created":"2023-05-15","cited_by_count":21,"area":null},{"id":"2308.13431","title":"Six Lectures on Linearized Neural Networks","created":"2023-08-25","cited_by_count":20,"area":null},{"id":"2203.01572","title":"Data Augmentation as Feature Manipulation","created":"2022-03-03","cited_by_count":18,"area":null},{"id":"2208.03113","title":"On the non-universality of deep learning: quantifying the cost of symmetry","created":"2022-08-05","cited_by_count":18,"area":null},{"id":"2303.13458","title":"Optimization Dynamics of Equivariant and Augmented Neural Networks","created":"2023-03-23","cited_by_count":18,"area":null},{"id":"2403.03103","title":"Emergent Equivariance in Deep Ensembles","created":"2024-03-05","cited_by_count":18,"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":"2204.00887","title":"Dimensionless machine learning: Imposing exact units equivariance","created":"2022-04-02","cited_by_count":17,"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":"2308.10436","title":"Approximately Equivariant Graph Networks","created":"2023-08-21","cited_by_count":16,"area":null},{"id":"2209.07238","title":"Generalization Properties of NAS under Activation and Skip Connection Search","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2210.13512","title":"Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2106.07148","title":"On the Sample Complexity of Learning under Invariance and Geometric Stability","created":"2021-06-14","cited_by_count":13,"area":null},{"id":"2209.14991","title":"Machine learning and invariant theory","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2401.01869","title":"On the hardness of learning under symmetries","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2406.12409","title":"Translation Equivariant Transformer Neural Processes","created":"2024-06-18","cited_by_count":13,"area":null},{"id":"2309.04268","title":"Optimal Rate of Kernel Regression in Large Dimensions","created":"2023-09-08","cited_by_count":11,"area":null},{"id":"2207.06456","title":"Graph Neural Network Bandits","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2301.07605","title":"Strong inductive biases provably prevent harmless interpolation","created":"2023-01-18","cited_by_count":10,"area":null},{"id":"2301.13724","title":"Towards fully covariant machine learning","created":"2023-01-31","cited_by_count":10,"area":null},{"id":"2311.13774","title":"Learning Hierarchical Polynomials with Three-Layer Neural Networks","created":"2023-11-23","cited_by_count":9,"area":null},{"id":"2402.08010","title":"Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning","created":"2024-02-12","cited_by_count":9,"area":null},{"id":"2406.13488","title":"Approximately Equivariant Neural Processes","created":"2024-06-19","cited_by_count":8,"area":null},{"id":"2410.01452","title":"Ensembles provably learn equivariance through data augmentation","created":"2024-10-02","cited_by_count":8,"area":null},{"id":"2410.05499","title":"Unitary convolutions for learning on graphs and groups","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2305.00979","title":"Spectral clustering in the Gaussian mixture block model","created":"2023-04-29","cited_by_count":7,"area":null},{"id":"2404.10727","title":"How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model","created":"2024-04-16","cited_by_count":7,"area":null},{"id":"2107.14324","title":"Deep Networks Provably Classify Data on Curves","created":"2021-07-29","cited_by_count":6,"area":null},{"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":"2402.10164","title":"Random features and polynomial rules","created":"2024-02-15","cited_by_count":6,"area":null},{"id":"2502.19758","title":"Learning with Exact Invariances in Polynomial Time","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2406.03171","title":"High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2410.16972","title":"Sample-efficient Bayesian Optimisation Using Known Invariances","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2505.20132","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2606.24418","title":"Data Augmentation: A Fourier Analysis Perspective","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2207.03485","title":"On Non-Linear operators for Geometric Deep Learning","created":"2022-07-06","cited_by_count":3,"area":null},{"id":"2210.06741","title":"Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2402.06855","title":"For Better or For Worse? Learning Minimum Variance Features With Label Augmentation","created":"2024-02-10","cited_by_count":3,"area":null},{"id":"2506.13714","title":"Understanding Learning Invariance in Deep Linear Networks","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2510.02532","title":"Learning Multi-Index Models with Hyper-Kernel Ridge Regression","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2512.24420","title":"Virasoro Symmetry in Neural Network Field Theories","created":"2025-12-30","cited_by_count":3,"area":null},{"id":"2609.07031","title":"Efficient Learning and Symmetry Discovery under Exact Invariances","created":"2026-09-07","cited_by_count":3,"area":null},{"id":"2303.00351","title":"Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2308.06271","title":"Rotation-Invariant Random Features Provide a Strong Baseline for Machine Learning on 3D Point Clouds","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2405.19995","title":"Symmetries in Overparametrized Neural Networks: A Mean-Field View","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2409.00915","title":"On the Pinsker bound of inner product kernel regression in large dimensions","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2503.00504","title":"On the Saturation Effects of Spectral Algorithms in Large Dimensions","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2105.14058","title":"Symmetry-driven graph neural networks","created":"2021-05-28","cited_by_count":1,"area":null},{"id":"2109.12784","title":"Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2305.13141","title":"Tight conditions for when the NTK approximation is valid","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2408.08823","title":"Optimal Symmetries in Binary Classification","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2602.20370","title":"Quantitative Approximation Rates for Group Equivariant Learning","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2604.13410","title":"Estimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.23591","title":"Asymmetric Scaling Laws from Sparse Features","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.10913","title":"Conservation Laws from Data Symmetry in Neural Networks","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2609.08133","title":"Sparse Data Augmentation for Optimization with Provable Guarantees","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2106.13786","title":"Data efficiency in graph networks through equivariance","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2310.01739","title":"Randomized Dimension Reduction with Statistical Guarantees","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2403.01671","title":"Approximating invariant functions with the sorting trick is theoretically justified","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2412.18756","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","created":"2024-12-25","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":"2606.01090","title":"Measuring the Symmetry--Data Exchange Rate","created":"2026-05-31","cited_by_count":0,"area":null}],"next_cursor":null}