{"total":30,"rows":[{"id":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56,"area":null},{"id":"2207.05952","title":"Implicit regularization of dropout","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2205.12101","title":"Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width","created":"2022-05-24","cited_by_count":17,"area":null},{"id":"2405.05409","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","created":"2024-05-08","cited_by_count":17,"area":null},{"id":"2504.09484","title":"An overview of condensation phenomenon in deep learning","created":"2025-04-13","cited_by_count":17,"area":null},{"id":"2305.12133","title":"Loss Spike in Training Neural Networks","created":"2023-05-20","cited_by_count":16,"area":null},{"id":"2401.08309","title":"Anchor function: a type of benchmark functions for studying language models","created":"2024-01-16","cited_by_count":11,"area":null},{"id":"2405.17299","title":"Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2510.06954","title":"From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics","created":"2025-10-08","cited_by_count":10,"area":null},{"id":"2305.09947","title":"Understanding the Initial Condensation of Convolutional Neural Networks","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2211.11623","title":"Linear Stability Hypothesis and Rank Stratification for Nonlinear Models","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2307.08921","title":"Optimistic Estimate Uncovers the Potential of Nonlinear Models","created":"2023-07-18","cited_by_count":5,"area":null},{"id":"2402.15958","title":"On the dynamics of three-layer neural networks: initial condensation","created":"2024-02-25","cited_by_count":3,"area":null},{"id":"2405.13721","title":"Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2409.16697","title":"Numerical Approximation Capacity of Neural Networks with Bounded Parameters: Do Limits Exist, and How Can They Be Measured?","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.20119","title":"On Multi-Stage Loss Dynamics in Neural Networks: Mechanisms of Plateau and Descent Stages","created":"2024-10-26","cited_by_count":1,"area":null},{"id":"2505.14777","title":"KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2605.04396","title":"Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2405.03095","title":"Loss Jump During Loss Switch in Solving PDEs with Neural Networks","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2405.13787","title":"Disentangle Sample Size and Initialization Effect on Perfect Generalization for Single-Neuron Target","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2406.18035","title":"Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2504.08628","title":"Gradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2505.17919","title":"KITINet: KInetic Theory Inspired Inter-Channel Information Exchange for Residual Networks","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.04613","title":"DeePoly: A High-Order Accuracy Scientific Machine Learning Framework for Function Approximation and Solving PDEs","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2510.03303","title":"Machine Learning and Control: Foundations, Advances, and Perspectives","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2605.26489","title":"The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.17945","title":"Small Initialization Matters for Large Language Models","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.02373","title":"Percolation Dynamics in Optimization: Variance Cascades and Nested Symmetry","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2610.04533","title":"Weight Decay and Neuron Condensation: A Three-Stage Analysis of Two-Layer ReLU Networks","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}