{"total":32,"rows":[{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107,"area":null},{"id":"2102.13219","title":"Learning with invariances in random features and kernel models","created":"2021-02-25","cited_by_count":89,"area":null},{"id":"2210.08566","title":"Theory for Equivariant Quantum Neural Networks","created":"2022-10-16","cited_by_count":62,"area":null},{"id":"2407.12332","title":"Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition","created":"2024-07-17","cited_by_count":36,"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":"2303.14269","title":"The Exact Sample Complexity Gain from Invariances for Kernel Regression","created":"2023-03-24","cited_by_count":28,"area":null},{"id":"2310.09753","title":"When can transformers reason with abstract symbols?","created":"2023-10-15","cited_by_count":24,"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":"2305.08404","title":"Theoretical Analysis of Inductive Biases in Deep Convolutional Networks","created":"2023-05-15","cited_by_count":21,"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":"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":"2303.00198","title":"Convolutional Visual Prompt for Robust Visual Perception","created":"2023-03-01","cited_by_count":17,"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":"2303.05369","title":"Data-dependent Generalization Bounds via Variable-Size Compressibility","created":"2023-03-09","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":"2410.01452","title":"Ensembles provably learn equivariance through data augmentation","created":"2024-10-02","cited_by_count":8,"area":null},{"id":"2305.01034","title":"Model-agnostic Measure of Generalization Difficulty","created":"2023-05-01","cited_by_count":7,"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":"2403.15707","title":"Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs","created":"2024-03-23","cited_by_count":5,"area":null},{"id":"2406.15941","title":"Towards Exact Computation of Inductive Bias","created":"2024-06-22","cited_by_count":5,"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":"2603.04807","title":"Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.20967","title":"Hard labels sampled from sparse targets mislead rotation invariant algorithms","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2103.01887","title":"Self-Regularity of Non-Negative Output Weights for Overparameterized Two-Layer Neural Networks","created":"2021-03-02","cited_by_count":0,"area":null},{"id":"2103.10656","title":"Beyond Linear Subspace Clustering: A Comparative Study of Nonlinear Manifold Clustering Algorithms","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2307.02693","title":"Kernels, Data & Physics","created":"2023-07-05","cited_by_count":0,"area":null},{"id":"2403.02697","title":"Noise misleads rotation invariant algorithms on sparse targets","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2408.04277","title":"Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNs","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2506.17558","title":"SynDaCaTE: A Synthetic Dataset For Evaluating Part-Whole Hierarchical Inference","created":"2025-06-21","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":"2604.23427","title":"On (not) learning the M\\\"obius function","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2610.12571","title":"An all-transistor physical-learning transformer can be trained to perform in-context learning","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}