{"total":85,"rows":[{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"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":"2208.05512","title":"Imbalance Trouble: Revisiting Neural-Collapse Geometry","created":"2022-08-10","cited_by_count":80,"area":null},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"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":"2501.04697","title":"Grokking at the Edge of Numerical Stability","created":"2025-01-08","cited_by_count":46,"area":null},{"id":"2305.11788","title":"Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability","created":"2023-05-19","cited_by_count":42,"area":null},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41,"area":null},{"id":"2103.15209","title":"Understanding the role of importance weighting for deep learning","created":"2021-03-28","cited_by_count":39,"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":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2402.15926","title":"Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency","created":"2024-02-24","cited_by_count":35,"area":null},{"id":"2106.05932","title":"Early-stopped neural networks are consistent","created":"2021-06-10","cited_by_count":34,"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":"2403.08081","title":"Mechanics of Next Token Prediction with Self-Attention","created":"2024-03-12","cited_by_count":34,"area":null},{"id":"2107.00595","title":"Fast Margin Maximization via Dual Acceleration","created":"2021-07-01","cited_by_count":33,"area":null},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31,"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":"2202.13441","title":"Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond","created":"2022-02-27","cited_by_count":29,"area":null},{"id":"2303.01462","title":"Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization","created":"2023-03-02","cited_by_count":29,"area":null},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2502.01694","title":"Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation","created":"2025-02-02","cited_by_count":25,"area":"lr"},{"id":"2408.15417","title":"Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations","created":"2024-08-27","cited_by_count":24,"area":null},{"id":"2303.07608","title":"On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data","created":"2023-03-14","cited_by_count":23,"area":null},{"id":"2107.05074","title":"SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs","created":"2021-07-11","cited_by_count":22,"area":null},{"id":"2302.09235","title":"Generalization and Stability of Interpolating Neural Networks with Minimal Width","created":"2023-02-18","cited_by_count":21,"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":"2308.13431","title":"Six Lectures on Linearized Neural Networks","created":"2023-08-25","cited_by_count":20,"area":null},{"id":"2401.07187","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","created":"2024-01-14","cited_by_count":20,"area":null},{"id":"2110.07647","title":"Towards Understanding the Data Dependency of Mixup-style Training","created":"2021-10-14","cited_by_count":19,"area":null},{"id":"2102.12238","title":"Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm","created":"2021-02-24","cited_by_count":18,"area":null},{"id":"2111.06063","title":"On the Equivalence between Neural Network and Support Vector Machine","created":"2021-11-11","cited_by_count":17,"area":null},{"id":"2202.06915","title":"Stochastic linear optimization never overfits with quadratically-bounded losses on general data","created":"2022-02-14","cited_by_count":17,"area":null},{"id":"2406.08654","title":"Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization","created":"2024-06-12","cited_by_count":17,"area":null},{"id":"2403.10175","title":"A Short Survey on Importance Weighting for Machine Learning","created":"2024-03-15","cited_by_count":15,"area":null},{"id":"2208.02789","title":"Feature selection with gradient descent on two-layer networks in low-rotation regimes","created":"2022-08-04","cited_by_count":14,"area":null},{"id":"2402.18551","title":"Implicit Optimization Bias of Next-Token Prediction in Linear Models","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"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":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2105.06569","title":"The Dynamics of Gradient Descent for Overparametrized Neural Networks","created":"2021-05-13","cited_by_count":11,"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":"2410.14581","title":"Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection","created":"2024-10-18","cited_by_count":9,"area":null},{"id":"2502.13283","title":"Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2506.02336","title":"Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2209.07116","title":"On Generalization of Decentralized Learning with Separable Data","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2401.14846","title":"Understanding Domain Generalization: A Noise Robustness Perspective","created":"2024-01-26","cited_by_count":8,"area":null},{"id":"2303.01135","title":"Tight Risk Bounds for Gradient Descent on Separable Data","created":"2023-03-02","cited_by_count":7,"area":null},{"id":"2306.14381","title":"Gradient Descent Converges Linearly for Logistic Regression on Separable Data","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2405.13136","title":"Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs","created":"2024-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2504.04105","title":"Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2102.05198","title":"Statistical Inference for Polyak-Ruppert Averaged Zeroth-order Stochastic Gradient Algorithm","created":"2021-02-10","cited_by_count":6,"area":null},{"id":"2412.08424","title":"From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes","created":"2024-12-11","cited_by_count":6,"area":null},{"id":"2502.02132","title":"How Memory in Optimization Algorithms Implicitly Modifies the Loss","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2201.04545","title":"On generalization bounds for deep networks based on loss surface implicit regularization","created":"2022-01-12","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":"2210.06705","title":"From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2402.18884","title":"Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features","created":"2024-02-29","cited_by_count":5,"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":"2206.12739","title":"On how to avoid exacerbating spurious correlations when models are overparameterized","created":"2022-06-25","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":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2305.13471","title":"Fast Convergence in Learning Two-Layer Neural Networks with Separable Data","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2505.11370","title":"Understanding Nonlinear Implicit Bias via Region Counts in Input Space","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2505.22359","title":"Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2212.02457","title":"Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria","created":"2022-12-05","cited_by_count":1,"area":null},{"id":"2306.07544","title":"On Achieving Optimal Adversarial Test Error","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2502.05668","title":"The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks","created":"2025-02-08","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":"2105.03879","title":"Directional Convergence Analysis under Spherically Symmetric Distribution","created":"2021-05-09","cited_by_count":0,"area":null},{"id":"2305.17544","title":"Faster Margin Maximization Rates for Generic and Adversarially Robust Optimization Methods","created":"2023-05-27","cited_by_count":0,"area":null},{"id":"2310.03890","title":"Accelerated Neural Network Training with Rooted Logistic Objectives","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2310.19041","title":"On Linear Separation Capacity of Self-Supervised Representation Learning","created":"2023-10-29","cited_by_count":0,"area":null},{"id":"2512.14338","title":"Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.18946","title":"Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2603.02095","title":"On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.02920","title":"Efficient Logistic Regression with Mixture of Sigmoids","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2609.07868","title":"SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.33904","title":"On the Two Faces of Adam in Separable Linear Classification","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37745","title":"Optimizer-dependent training dynamics converge to the same one-third optimal data scaling","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02798","title":"Muon Learns Facts Better: Understanding the Role of Spectral Orthogonalization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.07131","title":"The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}