{"total":92,"rows":[{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2309.16620","title":"Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit","created":"2023-09-28","cited_by_count":66,"area":null},{"id":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2107.11472","title":"Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers","created":"2021-07-23","cited_by_count":57,"area":null},{"id":"2105.09513","title":"Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions","created":"2021-05-20","cited_by_count":49,"area":null},{"id":"2107.01562","title":"Random Neural Networks in the Infinite Width Limit as Gaussian Processes","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2306.06179","title":"Hidden symmetries of ReLU networks","created":"2023-06-09","cited_by_count":39,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2402.02746","title":"Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization","created":"2024-02-05","cited_by_count":34,"area":null},{"id":"2106.04013","title":"The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization","created":"2021-06-07","cited_by_count":33,"area":null},{"id":"2505.02795","title":"HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2025-05-05","cited_by_count":31,"area":null},{"id":"2307.15092","title":"A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning","created":"2023-07-27","cited_by_count":22,"area":null},{"id":"2212.14457","title":"Bayesian Interpolation with Deep Linear Networks","created":"2022-12-29","cited_by_count":21,"area":null},{"id":"2307.06092","title":"Quantitative CLTs in Deep Neural Networks","created":"2023-07-12","cited_by_count":20,"area":null},{"id":"2302.12250","title":"Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2102.10492","title":"Deep ReLU Networks Preserve Expected Length","created":"2021-02-21","cited_by_count":17,"area":null},{"id":"2303.09728","title":"The Cascaded Forward Algorithm for Neural Network Training","created":"2023-03-17","cited_by_count":17,"area":null},{"id":"2505.24333","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","created":"2025-05-30","cited_by_count":17,"area":null},{"id":"2509.10167","title":"The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram","created":"2025-09-12","cited_by_count":17,"area":null},{"id":"2102.09924","title":"A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions","created":"2021-02-19","cited_by_count":14,"area":null},{"id":"2105.07741","title":"Activation function design for deep networks: linearity and effective initialisation","created":"2021-05-17","cited_by_count":13,"area":null},{"id":"2212.07295","title":"Maximal Initial Learning Rates in Deep ReLU Networks","created":"2022-12-14","cited_by_count":11,"area":null},{"id":"2306.00945","title":"CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2311.18718","title":"The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2104.00277","title":"A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions","created":"2021-04-01","cited_by_count":9,"area":null},{"id":"2305.07810","title":"Depth Dependence of $\\mu$P Learning Rates in ReLU MLPs","created":"2023-05-13","cited_by_count":9,"area":null},{"id":"2409.01696","title":"On the Vulnerability of Skip Connections to Model Inversion Attacks","created":"2024-09-03","cited_by_count":9,"area":null},{"id":"2208.02349","title":"Graph Neural Networks Extract High-Resolution Cultivated Land Maps from Sentinel-2 Image Series","created":"2022-08-03","cited_by_count":6,"area":null},{"id":"2208.12190","title":"CAS4DL: Christoffel Adaptive Sampling for function approximation via Deep Learning","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2305.07715","title":"Field theory for optimal signal propagation in ResNets","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2406.07961","title":"Accurate Explanation Model for Image Classifiers using Class Association Embedding","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2506.16884","title":"The Importance of Being Lazy: Scaling Limits of Continual Learning","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2106.02260","title":"Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks","created":"2021-06-04","cited_by_count":5,"area":null},{"id":"2109.08958","title":"AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2303.03918","title":"Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2310.07765","title":"Feature Learning and Generalization in Deep Networks with Orthogonal Weights","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2402.02969","title":"Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2405.16630","title":"Bayesian Inference with Deep Weakly Nonlinear Networks","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2101.03850","title":"Deep Neural Networks to Recover Unknown Physical Parameters from Oscillating Time Series","created":"2021-01-11","cited_by_count":4,"area":null},{"id":"2101.04243","title":"A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks","created":"2021-01-12","cited_by_count":4,"area":null},{"id":"2405.06299","title":"Cross-domain Learning Framework for Tracking Users in RIS-aided Multi-band ISAC Systems with Sparse Labeled Data","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2210.05212","title":"On Scrambling Phenomena for Randomly Initialized Recurrent Networks","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2302.09712","title":"Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization","created":"2023-02-20","cited_by_count":3,"area":null},{"id":"2306.11668","title":"Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2310.18725","title":"The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks","created":"2023-10-28","cited_by_count":3,"area":null},{"id":"2403.11026","title":"EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration","created":"2024-03-16","cited_by_count":3,"area":null},{"id":"2410.05572","title":"Improved deep learning of chaotic dynamical systems with multistep penalty losses","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2505.02604","title":"Connecting Independently Trained Modes via Layer-Wise Connectivity","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2205.10456","title":"PSO-Convolutional Neural Networks with Heterogeneous Learning Rate","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2212.12018","title":"Langevin algorithms for Markovian Neural Networks and Deep Stochastic control","created":"2022-12-22","cited_by_count":2,"area":null},{"id":"2307.01930","title":"Learning ECG Signal Features Without Backpropagation Using Linear Laws","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2402.07366","title":"Bayesian Deep Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2103.12499","title":"Initializing ReLU networks in an expressive subspace of weights","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2111.02154","title":"Regularization by Misclassification in ReLU Neural Networks","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2212.14718","title":"Langevin algorithms for very deep Neural Networks with application to image classification","created":"2022-12-27","cited_by_count":1,"area":null},{"id":"2301.06786","title":"Ensemble Reservoir Computing for Dynamical Systems: Prediction of Phase-Space Stable Region for Hadron Storage Rings","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2301.06956","title":"Expected Gradients of Maxout Networks and Consequences to Parameter Initialization","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2303.06815","title":"On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2305.06139","title":"A Neural Emulator for Uncertainty Estimation of Fire Propagation","created":"2023-05-10","cited_by_count":1,"area":null},{"id":"2309.01592","title":"Les Houches Lectures on Deep Learning at Large & Infinite Width","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2311.10857","title":"WATUNet: A Deep Neural Network for Segmentation of Volumetric Sweep Imaging Ultrasound","created":"2023-11-17","cited_by_count":1,"area":null},{"id":"2311.14658","title":"Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2406.09877","title":"Federated Learning with Flexible Architectures","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2407.00568","title":"Divide And Conquer: Learning Chaotic Dynamical Systems With Multistep Penalty Neural Ordinary Differential Equations","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2407.08232","title":"SwishReLU: A Unified Approach to Activation Functions for Enhanced Deep Neural Networks Performance","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2408.04819","title":"Interventional Causal Structure Discovery over Graphical Models with Convergence and Optimality Guarantees","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2503.01086","title":"FAIR: Facilitating Artificial Intelligence Resilience in Manufacturing Industrial Internet","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2503.08489","title":"A Triple-Inertial Accelerated Alternating Optimization Method for Deep Learning Training","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2504.13355","title":"Denoising and Reconstruction of Nonlinear Dynamics using Truncated Reservoir Computing","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2509.15368","title":"Stochastic Sample Approximations of (Local) Moduli of Continuity","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2101.01178","title":"Advances in Electron Microscopy with Deep Learning","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2104.10727","title":"Deep limits and cut-off phenomena for neural networks","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2112.14314","title":"Improving Prediction of Cognitive Performance using Deep Neural Networks in Sparse Data","created":"2021-12-28","cited_by_count":0,"area":null},{"id":"2210.02411","title":"Dynamical Isometry for Residual Networks","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2305.18445","title":"Intelligent gradient amplification for deep neural networks","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2309.03825","title":"Prime and Modulate Learning: Generation of forward models with signed back-propagation and environmental cues","created":"2023-09-07","cited_by_count":0,"area":null},{"id":"2312.12578","title":"Improving the Expressive Power of Deep Neural Networks through Integral Activation Transform","created":"2023-12-19","cited_by_count":0,"area":null},{"id":"2404.18041","title":"Variational Optimization for Quantum Problems using Deep Generative Networks","created":"2024-04-28","cited_by_count":0,"area":null},{"id":"2411.12052","title":"HoGA: Higher-Order Graph Attention via Diversity-Aware k-Hop Sampling","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2412.01400","title":"Fire-Image-DenseNet (FIDN) for predicting wildfire burnt area using remote sensing data","created":"2024-12-02","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":"2508.04193","title":"Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2508.11672","title":"Revealing Neurocognitive and Behavioral Patterns by Unsupervised Manifold Learning from Dynamic Brain Data","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2602.01308","title":"Dispelling the Curse of Singularities in Neural Network Optimizations","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.10949","title":"Optimal Initialization in Depth: Lyapunov Initialization and Limit Theorems for Deep Leaky ReLU Networks","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2605.05113","title":"How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.29152","title":"Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.17013","title":"Exploding and vanishing gradients in deep neural networks: the effect of residual connections","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.14638","title":"Randomly initialized autoencoders: fixed points and edge-of-chaos","created":"2026-07-28","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}],"next_cursor":null}