{"total":71,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121,"area":null},{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"area":null},{"id":"2106.15933","title":"Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity","created":"2021-06-30","cited_by_count":85,"area":null},{"id":"2110.13905","title":"Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias","created":"2021-10-26","cited_by_count":83,"area":null},{"id":"2311.18817","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","created":"2023-11-30","cited_by_count":80,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73,"area":null},{"id":"2102.09769","title":"On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent","created":"2021-02-19","cited_by_count":70,"area":null},{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42,"area":null},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39,"area":null},{"id":"2209.15055","title":"Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions","created":"2022-09-29","cited_by_count":38,"area":null},{"id":"2407.12332","title":"Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition","created":"2024-07-17","cited_by_count":36,"area":null},{"id":"2102.07346","title":"On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2110.02732","title":"On Margin Maximization in Linear and ReLU Networks","created":"2021-10-06","cited_by_count":34,"area":null},{"id":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2305.16038","title":"Implicit bias of SGD in $L_{2}$-regularized linear DNNs: One-way jumps from high to low rank","created":"2023-05-25","cited_by_count":29,"area":null},{"id":"2205.14814","title":"Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding","created":"2022-05-30","cited_by_count":28,"area":null},{"id":"2201.11729","title":"Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks","created":"2022-01-27","cited_by_count":27,"area":null},{"id":"2307.01827","title":"Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses","created":"2023-07-04","cited_by_count":26,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2210.03820","title":"The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks","created":"2022-10-07","cited_by_count":25,"area":null},{"id":"2106.06573","title":"Understanding Deflation Process in Over-parametrized Tensor Decomposition","created":"2021-06-11","cited_by_count":20,"area":null},{"id":"2101.02533","title":"Towards Understanding Learning in Neural Networks with Linear Teachers","created":"2021-01-07","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":"2402.06323","title":"How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers","created":"2024-02-09","cited_by_count":18,"area":null},{"id":"2101.01152","title":"Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise","created":"2021-01-04","cited_by_count":17,"area":null},{"id":"2107.01641","title":"A Theoretical Analysis of Fine-tuning with Linear Teachers","created":"2021-07-04","cited_by_count":17,"area":null},{"id":"2205.13647","title":"Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures","created":"2022-05-26","cited_by_count":17,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2105.13831","title":"Implicit Regularization in Matrix Sensing via Mirror Descent","created":"2021-05-28","cited_by_count":11,"area":null},{"id":"2403.06392","title":"Towards Robust Out-of-Distribution Generalization Bounds via Sharpness","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2602.16340","title":"The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2110.06482","title":"Parallel Deep Neural Networks Have Zero Duality Gap","created":"2021-10-13","cited_by_count":9,"area":null},{"id":"2310.02396","title":"Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse","created":"2023-10-03","cited_by_count":9,"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":"2101.07150","title":"Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2202.13328","title":"Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization","created":"2022-02-27","cited_by_count":7,"area":null},{"id":"2312.12657","title":"The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2406.16300","title":"Landscaping Linear Mode Connectivity","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2111.11542","title":"Depth Without the Magic: Inductive Bias of Natural Gradient Descent","created":"2021-11-22","cited_by_count":5,"area":null},{"id":"2206.08558","title":"How You Start Matters for Generalization","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2208.05640","title":"Adaptive and Implicit Regularization for Matrix Completion","created":"2022-08-11","cited_by_count":5,"area":null},{"id":"2209.13394","title":"Magnitude and Angle Dynamics in Training Single ReLU Neurons","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2211.04589","title":"Finite Sample Identification of Wide Shallow Neural Networks with Biases","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2406.04981","title":"The Price of Implicit Bias in Adversarially Robust Generalization","created":"2024-06-07","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":"2402.03579","title":"Deconstructing the Goldilocks Zone of Neural Network Initialization","created":"2024-02-05","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":"2102.13522","title":"Experiments with Rich Regime Training for Deep Learning","created":"2021-02-26","cited_by_count":2,"area":null},{"id":"2412.16765","title":"Optimization Insights into Deep Diagonal Linear Networks","created":"2024-12-21","cited_by_count":2,"area":null},{"id":"2506.12284","title":"GrokAlign: Geometric Characterisation and Acceleration of Grokking","created":"2025-06-14","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":"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":"2206.15058","title":"A note on Linear Bottleneck networks and their Transition to Multilinearity","created":"2022-06-30","cited_by_count":1,"area":null},{"id":"2311.15404","title":"Applying statistical learning theory to deep learning","created":"2023-11-26","cited_by_count":1,"area":null},{"id":"2406.06354","title":"On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2507.19680","title":"Feature learning is decoupled from generalization in high capacity neural networks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2508.20344","title":"Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization","created":"2025-08-28","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":"2110.07557","title":"AIR-Net: Adaptive and Implicit Regularization Neural Network for Matrix Completion","created":"2021-10-12","cited_by_count":0,"area":null},{"id":"2411.06916","title":"Slowing Down Forgetting in Continual Learning","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2605.08464","title":"The Geometric Structure of Models Learning Sparse Data","created":"2026-05-08","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}],"next_cursor":null}