{"total":57,"rows":[{"id":"2310.19793","title":"On Learning Gaussian Multi-index Models with Gradient Flow","created":"2023-10-30","cited_by_count":57,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2309.15111","title":"SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem","created":"2023-09-26","cited_by_count":39,"area":null},{"id":"2407.03475","title":"How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks","created":"2024-07-03","cited_by_count":31,"area":"distill"},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"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":"2505.17863","title":"The emergence of sparse attention: impact of data distribution and benefits of repetition","created":"2025-05-23","cited_by_count":25,"area":null},{"id":"2509.24882","title":"Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime","created":"2025-09-29","cited_by_count":20,"area":null},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19,"area":null},{"id":"2403.08699","title":"Implicit Regularization of Gradient Flow on One-Layer Softmax Attention","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2405.18273","title":"Synchronization on circles and spheres with nonlinear interactions","created":"2024-05-28","cited_by_count":17,"area":null},{"id":"2306.06479","title":"Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs","created":"2023-06-10","cited_by_count":16,"area":null},{"id":"2508.12837","title":"Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points","created":"2025-08-18","cited_by_count":16,"area":null},{"id":"2305.12467","title":"Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks","created":"2023-05-21","cited_by_count":15,"area":null},{"id":"2512.20607","title":"Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures","created":"2025-12-23","cited_by_count":15,"area":null},{"id":"2405.20763","title":"Improving Generalization and Convergence by Enhancing Implicit Regularization","created":"2024-05-31","cited_by_count":14,"area":null},{"id":"2506.06489","title":"Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2503.06982","title":"Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2305.05448","title":"Robust Implicit Regularization via Weight Normalization","created":"2023-05-09","cited_by_count":12,"area":null},{"id":"2402.09226","title":"Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2402.09142","title":"When Representations Align: Universality in Representation Learning Dynamics","created":"2024-02-14","cited_by_count":10,"area":null},{"id":"2602.03655","title":"Sequential Group Composition: A Window into the Mechanics of Deep Learning","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2406.12763","title":"Implicit Bias of Mirror Flow on Separable Data","created":"2024-06-18","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":"2506.02269","title":"A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2402.05626","title":"Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding","created":"2024-02-08","cited_by_count":6,"area":null},{"id":"2509.24914","title":"Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2402.05013","title":"Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth","created":"2024-02-07","cited_by_count":5,"area":null},{"id":"2410.08309","title":"Swing-by Dynamics in Concept Learning and Compositional Generalization","created":"2024-10-10","cited_by_count":5,"area":"diffusion"},{"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":"2307.07410","title":"Implicit regularization in AI meets generalized hardness of approximation in optimization -- Sharp results for diagonal linear networks","created":"2023-07-13","cited_by_count":4,"area":null},{"id":"2311.14387","title":"Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling","created":"2023-11-24","cited_by_count":4,"area":null},{"id":"2406.12615","title":"When Are Bias-Free ReLU Networks Effectively Linear Networks?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2505.21722","title":"Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2509.18766","title":"Diagonal Linear Networks and the Lasso Regularization Path","created":"2025-09-23","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":"2311.15051","title":"Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults","created":"2023-11-25","cited_by_count":3,"area":null},{"id":"2407.09845","title":"Towards Understanding Epoch-wise Double descent in Two-layer Linear Neural Networks","created":"2024-07-13","cited_by_count":3,"area":null},{"id":"2510.01930","title":"Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2602.19143","title":"Incremental Learning of Sparse Attention Patterns in Transformers","created":"2026-02-22","cited_by_count":2,"area":null},{"id":"2603.03993","title":"Specialization of softmax attention heads: insights from the high-dimensional single-location model","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2606.23198","title":"Incremental Learning in Mirror Flows","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2402.07626","title":"Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2410.24050","title":"A Mechanistic Study of Transformers Training Dynamics","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2603.20967","title":"Hard labels sampled from sparse targets mislead rotation invariant algorithms","created":"2026-03-21","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":"2603.10397","title":"On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD","created":"2026-03-11","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":"2607.10869","title":"Singular perturbations and hierarchical learning in two-layer neural networks","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.00420","title":"How Temporal Correlations Shape Memory in Linear Recurrent Neural Networks","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.09595","title":"Teacher Geometry Shapes Learnability in Teacher-Student Networks","created":"2026-09-09","cited_by_count":0,"area":"distill"},{"id":"2609.13057","title":"Benign Loss Landscapes Can Coexist with Worst-Case Hardness","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.34756","title":"Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04142","title":"Ideal Paths for Approximating Logistic Gradient Descent Trajectories at Large Initialization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.06120","title":"Mind the Drift: Diagonal Linear Networks Under Large Learning Rates","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.16868","title":"From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}