{"total":44,"rows":[{"id":"2409.14623","title":"From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks","created":"2024-09-22","cited_by_count":49,"area":null},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2501.18915","title":"Algebra Unveils Deep Learning -- An Invitation to Neuroalgebraic Geometry","created":"2025-01-31","cited_by_count":21,"area":null},{"id":"2402.07193","title":"Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent","created":"2024-02-11","cited_by_count":19,"area":null},{"id":"2502.05300","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2405.12888","title":"Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows","created":"2024-05-21","cited_by_count":11,"area":null},{"id":"2310.01225","title":"A path-norm toolkit for modern networks: consequences, promises and challenges","created":"2023-10-02","cited_by_count":10,"area":null},{"id":"2501.15556","title":"Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2502.21009","title":"Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2505.12387","title":"Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2506.06194","title":"Transformative or Conservative? Conservation laws for ResNets and Transformers","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2504.12801","title":"Sign-In to the Lottery: Reparameterizing Sparse Training From Scratch","created":"2025-04-17","cited_by_count":6,"area":null},{"id":"2602.00693","title":"Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2602.19799","title":"Path-conditioned training: a principled way to rescale ReLU neural networks","created":"2026-02-23","cited_by_count":6,"area":null},{"id":"2602.20062","title":"A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2401.07085","title":"Three Mechanisms of Feature Learning in a Linear Network","created":"2024-01-13","cited_by_count":4,"area":null},{"id":"2402.18905","title":"Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2405.15006","title":"A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2508.07370","title":"Intrinsic training dynamics of deep neural networks","created":"2025-08-10","cited_by_count":4,"area":null},{"id":"2511.01137","title":"Regularization Implies balancedness in the deep linear network","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2603.02064","title":"Never Saddle for Reparameterized Steepest Descent as Mirror Flow","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2601.06597","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","created":"2026-01-10","cited_by_count":3,"area":null},{"id":"2605.18319","title":"The Symmetries of Three-Layer ReLU Networks","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2605.19458","title":"Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2605.31484","title":"Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2606.30509","title":"Muon learns balanced solutions in matrix factorization without slow saddle-to-saddle dynamics","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2412.16765","title":"Optimization Insights into Deep Diagonal Linear Networks","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2502.16977","title":"Convergence of Shallow ReLU Networks on Weakly Interacting Data","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2507.06367","title":"The Riemannian Geometry Associated to Gradient Flows of Linear Convolutional Networks","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2607.23967","title":"Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries","created":"2026-07-27","cited_by_count":2,"area":null},{"id":"2509.26149","title":"Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2606.10913","title":"Conservation Laws from Data Symmetry in Neural Networks","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.17816","title":"Conservation Laws for Modern Neural Architectures","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.12332","title":"Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2608.06766","title":"Hidden Gauge Controls Feature Specialization in ReLU Networks","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2604.07405","title":"Conservation Law Breaking at the Edge of Stability: A Spectral Theory of Non-Convex Neural Network Optimization","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.14430","title":"Three-Phase Transformer","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.01288","title":"A Theory of Saddle Escape in Deep Nonlinear Networks","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2607.07845","title":"Explaining Near-Zero Hessian Eigenvalues Through Approximate Symmetries in Neural Networks","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2609.13057","title":"Benign Loss Landscapes Can Coexist with Worst-Case Hardness","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.34549","title":"On Parameter Symmetries and Conservation Laws in Gradient Flow","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01981","title":"Universal interpolation for deep residual self-attention networks","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.09356","title":"Global Exponential Convergence of Two-Layer Linear Network Training","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}