{"total":43,"rows":[{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2203.07379","title":"Quantitative Gaussian Approximation of Randomly Initialized Deep Neural Networks","created":"2022-03-14","cited_by_count":25,"area":null},{"id":"2307.06092","title":"Quantitative CLTs in Deep Neural Networks","created":"2023-07-12","cited_by_count":20,"area":null},{"id":"2111.03175","title":"Rate of Convergence of Polynomial Networks to Gaussian Processes","created":"2021-11-04","cited_by_count":13,"area":null},{"id":"2305.02334","title":"Structures of Neural Network Effective Theories","created":"2023-05-03","cited_by_count":13,"area":null},{"id":"2312.11737","title":"Wide Deep Neural Networks with Gaussian Weights are Very Close to Gaussian Processes","created":"2023-12-18","cited_by_count":13,"area":null},{"id":"2406.03260","title":"Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers","created":"2024-06-05","cited_by_count":12,"area":null},{"id":"2304.04010","title":"Non-asymptotic approximations of Gaussian neural networks via second-order Poincar\\'e inequalities","created":"2023-04-08","cited_by_count":11,"area":null},{"id":"2306.16308","title":"Gaussian random field approximation via Stein's method with applications to wide random neural networks","created":"2023-06-28","cited_by_count":11,"area":null},{"id":"2405.17538","title":"Bayesian RG Flow in Neural Network Field Theories","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2505.24849","title":"Statistical mechanics of extensive-width Bayesian neural networks near interpolation","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2111.12143","title":"Critical Initialization of Wide and Deep Neural Networks through Partial Jacobians: General Theory and Applications","created":"2021-11-23","cited_by_count":8,"area":null},{"id":"2306.16932","title":"A Quantitative Functional Central Limit Theorem for Shallow Neural Networks","created":"2023-06-29","cited_by_count":8,"area":null},{"id":"2403.08750","title":"Neural reproducing kernel Banach spaces and representer theorems for deep networks","created":"2024-03-13","cited_by_count":8,"area":null},{"id":"2111.11954","title":"Depth induces scale-averaging in overparameterized linear Bayesian neural networks","created":"2021-11-23","cited_by_count":7,"area":null},{"id":"2505.03577","title":"Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime","created":"2025-05-06","cited_by_count":6,"area":null},{"id":"2405.16630","title":"Bayesian Inference with Deep Weakly Nonlinear Networks","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2410.05626","title":"On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory","created":"2024-10-08","cited_by_count":5,"area":null},{"id":"2507.12686","title":"Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights","created":"2025-07-16","cited_by_count":5,"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":"2304.03385","title":"Wide neural networks: From non-gaussian random fields at initialization to the NTK geometry of training","created":"2023-04-06","cited_by_count":3,"area":null},{"id":"2405.09541","title":"Spectral complexity of deep neural networks","created":"2024-05-15","cited_by_count":3,"area":null},{"id":"2405.10229","title":"Random ReLU Neural Networks as Non-Gaussian Processes","created":"2024-05-16","cited_by_count":3,"area":null},{"id":"2405.16958","title":"Large Deviations of Gaussian Neural Networks with ReLU activation","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2407.18707","title":"Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2411.15267","title":"Proportional infinite-width infinite-depth limit for deep linear neural networks","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2505.19087","title":"Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2602.05779","title":"How Controlling the Variance can Improve Training Stability of Sparsely Activated DNNs and CNNs","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2204.12100","title":"Convergence of neural networks to Gaussian mixture distribution","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2504.06250","title":"Fractal and Regular Geometry of Deep Neural Networks","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2506.21894","title":"Thompson Sampling in Function Spaces via Neural Operators","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2509.01349","title":"Phase diagram and eigenvalue dynamics of stochastic gradient descent in multilayer neural networks","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2308.00858","title":"Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processes","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2411.16229","title":"Effective Non-Random Extreme Learning Machine","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2503.23982","title":"Deep Neural Nets as Hamiltonians","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2505.17000","title":"Critical Points of Random Neural Networks","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.22095","title":"Posterior Bayesian Neural Networks with Dependent Weights","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2510.24616","title":"Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2603.06023","title":"Large deviation principles for convolutional Bayesian neural networks","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2605.24072","title":"Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2608.26526","title":"High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.18166","title":"Lifting Finite-Sample Gaussian Approximation of Wide Neural Networks to Functional Convergence","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}