{"total":72,"rows":[{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649,"area":null},{"id":"2106.03253","title":"Tabular Data: Deep Learning is Not All You Need","created":"2021-06-06","cited_by_count":535,"area":null},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166,"area":null},{"id":"2104.13386","title":"Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems","created":"2021-04-27","cited_by_count":128,"area":null},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100,"area":null},{"id":"2406.11045","title":"Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks","created":"2024-06-16","cited_by_count":67,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2203.05071","title":"On the influence of over-parameterization in manifold based surrogates and deep neural operators","created":"2022-03-09","cited_by_count":29,"area":null},{"id":"2106.08619","title":"Locality defeats the curse of dimensionality in convolutional teacher-student scenarios","created":"2021-06-16","cited_by_count":26,"area":"distill"},{"id":"2302.00849","title":"Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent","created":"2023-02-02","cited_by_count":25,"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":"2212.06663","title":"Quantum Policy Gradient Algorithm with Optimized Action Decoding","created":"2022-12-13","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":"2208.01003","title":"What Can Be Learnt With Wide Convolutional Neural Networks?","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2106.12912","title":"Information Bottleneck: Exact Analysis of (Quantized) Neural Networks","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2407.10315","title":"Order parameters and phase transitions of continual learning in deep neural networks","created":"2024-07-14","cited_by_count":14,"area":null},{"id":"2509.14026","title":"Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks","created":"2025-09-17","cited_by_count":10,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2109.13392","title":"The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decoding","created":"2021-09-27","cited_by_count":8,"area":null},{"id":"2507.19703","title":"The wall confronting large language models","created":"2025-07-25","cited_by_count":8,"area":null},{"id":"2101.00232","title":"Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?","created":"2021-01-01","cited_by_count":7,"area":null},{"id":"2103.11775","title":"Measuring and modeling the motor system with machine learning","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2110.11886","title":"Conditionally Gaussian PAC-Bayes","created":"2021-10-22","cited_by_count":7,"area":null},{"id":"2301.12033","title":"Norm-based Generalization Bounds for Compositionally Sparse Neural Networks","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2108.06711","title":"Towards Understanding Theoretical Advantages of Complex-Reaction Networks","created":"2021-08-15","cited_by_count":6,"area":null},{"id":"2201.01954","title":"Federated Optimization of Smooth Loss Functions","created":"2022-01-06","cited_by_count":6,"area":null},{"id":"2302.14702","title":"Performance Limits of a Deep Learning-Enabled Text Semantic Communication under Interference","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2107.09532","title":"Estimation of a regression function on a manifold by fully connected deep neural networks","created":"2021-07-20","cited_by_count":5,"area":null},{"id":"2306.15337","title":"Homological Neural Networks: A Sparse Architecture for Multivariate Complexity","created":"2023-06-27","cited_by_count":5,"area":null},{"id":"2307.01177","title":"Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2404.15471","title":"Training all-mechanical neural networks for task learning through in situ backpropagation","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2411.04324","title":"Gradient Boosting Trees and Large Language Models for Tabular Data Few-Shot Learning","created":"2024-11-06","cited_by_count":5,"area":null},{"id":"2505.21208","title":"Input Convex Kolmogorov Arnold Networks","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2107.10199","title":"Distribution of Classification Margins: Are All Data Equal?","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2205.01421","title":"A Falsificationist Account of Artificial Neural Networks","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2301.04605","title":"Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions","created":"2023-01-11","cited_by_count":4,"area":null},{"id":"2305.17332","title":"Learning Capacity: A Measure of the Effective Dimensionality of a Model","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2112.09741","title":"Envisioning Future Deep Learning Theories: Some Basic Concepts and Characteristics","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2201.04194","title":"Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics","created":"2022-01-11","cited_by_count":3,"area":null},{"id":"2410.03801","title":"P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimization","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2509.16750","title":"Interpretable Clinical Classification with Kolmogorov-Arnold Networks","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2111.12963","title":"Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2202.10788","title":"Explicit Regularization via Regularizer Mirror Descent","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2206.07483","title":"Blind Estimation of a Doubly Selective OFDM Channel: A Deep Learning Algorithm and Theory","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2312.06887","title":"Understanding and Leveraging the Learning Phases of Neural Networks","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2101.07357","title":"Unsupervised Imputation of Non-ignorably Missing Data Using Importance-Weighted Autoencoders","created":"2021-01-18","cited_by_count":1,"area":null},{"id":"2208.14092","title":"Super-model ecosystem: A domain-adaptation perspective","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2212.14150","title":"A Dynamics Theory of Implicit Regularization in Deep Low-Rank Matrix Factorization","created":"2022-12-29","cited_by_count":1,"area":null},{"id":"2305.19889","title":"Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2307.00919","title":"Why do CNNs excel at feature extraction? A mathematical explanation","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2403.17467","title":"A Unified Kernel for Neural Network Learning","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2404.14451","title":"Generative Subspace Adversarial Active Learning for Outlier Detection in Multiple Views of High-dimensional Data","created":"2024-04-20","cited_by_count":1,"area":null},{"id":"2501.15757","title":"Efficiency Bottlenecks of Convolutional Kolmogorov-Arnold Networks: A Comprehensive Scrutiny with ImageNet, AlexNet, LeNet and Tabular Classification","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2501.17411","title":"A Genetic Algorithm-Based Approach for Automated Optimization of Kolmogorov-Arnold Networks in Classification Tasks","created":"2025-01-29","cited_by_count":1,"area":null},{"id":"2509.05130","title":"The Advantage of Fine-Grained Training","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2511.05585","title":"Depth-induced NTK: Bridging Over-parameterized Neural Networks and Deep Neural Kernels","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2602.13910","title":"Sufficient Conditions for Stability of Minimum-Norm Interpolating Deep ReLU Networks","created":"2026-02-14","cited_by_count":1,"area":null},{"id":"2101.00464","title":"Data-Driven Random Access Optimization in Multi-Cell IoT Networks with NOMA","created":"2021-01-02","cited_by_count":0,"area":null},{"id":"2106.13233","title":"Post-Selections in AI and How to Avoid Them","created":"2021-06-19","cited_by_count":0,"area":null},{"id":"2109.05934","title":"Task Guided Compositional Representation Learning for ZDA","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2112.02256","title":"Towards the One Learning Algorithm Hypothesis: A System-theoretic Approach","created":"2021-12-04","cited_by_count":0,"area":null},{"id":"2202.08299","title":"The learning phases in NN: From Fitting the Majority to Fitting a Few","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2208.01416","title":"Biologically Plausible Training of Deep Neural Networks Using a Top-down Credit Assignment Network","created":"2022-08-01","cited_by_count":0,"area":null},{"id":"2309.06774","title":"Fundamental Limits of Deep Learning-Based Binary Classifiers Trained with Hinge Loss","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2402.02449","title":"Surfing the modeling of PoS taggers in low-resource scenarios","created":"2024-02-04","cited_by_count":0,"area":null},{"id":"2403.00574","title":"Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2410.09926","title":"A resource-efficient model for deep kernel learning","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2501.08341","title":"Dissecting a Small Artificial Neural Network","created":"2025-01-03","cited_by_count":0,"area":null},{"id":"2503.23289","title":"Enhancing Physics-Informed Neural Networks with a Hybrid Parallel Kolmogorov-Arnold and MLP Architecture","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2510.10586","title":"Compositional Symmetry as Compression: Lie Pseudogroup Structure in Algorithmic Agents","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2602.14663","title":"Pseudo-differential-enhanced physics-informed neural networks","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.25033","title":"Epistemic Compression: The Case for Deliberate Ignorance in High-Stakes AI","created":"2026-03-26","cited_by_count":0,"area":null}],"next_cursor":null}