{"total":133,"rows":[{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427,"area":null},{"id":"2106.02073","title":"Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path","created":"2021-06-03","cited_by_count":158,"area":null},{"id":"2205.11508","title":"Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods","created":"2022-05-23","cited_by_count":149,"area":null},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132,"area":null},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102,"area":null},{"id":"2207.09640","title":"Test-Time Adaptation via Conjugate Pseudo-labels","created":"2022-07-20","cited_by_count":98,"area":null},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2108.00106","title":"Soft Calibration Objectives for Neural Networks","created":"2021-07-30","cited_by_count":92,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78,"area":null},{"id":"2204.03632","title":"The Effects of Regularization and Data Augmentation are Class Dependent","created":"2022-04-07","cited_by_count":67,"area":null},{"id":"2109.02355","title":"A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning","created":"2021-09-06","cited_by_count":57,"area":null},{"id":"2106.09017","title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","created":"2021-06-16","cited_by_count":50,"area":null},{"id":"2106.10865","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","created":"2021-06-21","cited_by_count":42,"area":null},{"id":"2212.09034","title":"Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs","created":"2022-12-18","cited_by_count":42,"area":null},{"id":"2301.00437","title":"Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data","created":"2023-01-01","cited_by_count":40,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","cited_by_count":36,"area":null},{"id":"2210.16658","title":"Perturbation Analysis of Neural Collapse","created":"2022-10-29","cited_by_count":35,"area":null},{"id":"2110.15403","title":"Selective Regression Under Fairness Criteria","created":"2021-10-28","cited_by_count":34,"area":null},{"id":"2305.13665","title":"Dual Focal Loss for Calibration","created":"2023-05-23","cited_by_count":33,"area":null},{"id":"2207.06343","title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2206.12569","title":"Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels","created":"2022-06-25","cited_by_count":25,"area":null},{"id":"2307.08114","title":"Tangent Model Composition for Ensembling and Continual Fine-tuning","created":"2023-07-16","cited_by_count":25,"area":null},{"id":"2402.03496","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","created":"2024-02-05","cited_by_count":25,"area":null},{"id":"2210.05021","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2212.12206","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","created":"2022-12-23","cited_by_count":24,"area":null},{"id":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20,"area":null},{"id":"2501.00961","title":"Uncovering Memorization Effect in the Presence of Spurious Correlations","created":"2025-01-01","cited_by_count":20,"area":null},{"id":"2207.09413","title":"SphereFed: Hyperspherical Federated Learning","created":"2022-07-19","cited_by_count":19,"area":null},{"id":"2307.01951","title":"A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks","created":"2023-07-04","cited_by_count":19,"area":null},{"id":"2305.16427","title":"Neural (Tangent Kernel) Collapse","created":"2023-05-25","cited_by_count":18,"area":null},{"id":"2311.14646","title":"More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory","created":"2023-11-24","cited_by_count":18,"area":null},{"id":"2102.12013","title":"Understanding and Mitigating Accuracy Disparity in Regression","created":"2021-02-24","cited_by_count":17,"area":null},{"id":"2109.07557","title":"CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations","created":"2021-09-15","cited_by_count":17,"area":null},{"id":"2302.00704","title":"Pathologies of Predictive Diversity in Deep Ensembles","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2307.16792","title":"Classification with Deep Neural Networks and Logistic Loss","created":"2023-07-31","cited_by_count":16,"area":null},{"id":"2101.06640","title":"Estimating informativeness of samples with Smooth Unique Information","created":"2021-01-17","cited_by_count":15,"area":null},{"id":"2402.01502","title":"Why do Random Forests Work? Understanding Tree Ensembles as Self-Regularizing Adaptive Smoothers","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2111.05198","title":"Harmless interpolation in regression and classification with structured features","created":"2021-11-09","cited_by_count":14,"area":null},{"id":"2112.03657","title":"Understanding Square Loss in Training Overparametrized Neural Network Classifiers","created":"2021-12-07","cited_by_count":14,"area":null},{"id":"2303.06484","title":"Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap","created":"2023-03-11","cited_by_count":14,"area":null},{"id":"2304.05187","title":"Automatic Gradient Descent: Deep Learning without Hyperparameters","created":"2023-04-11","cited_by_count":14,"area":null},{"id":"2306.13853","title":"A Unified Approach to Controlling Implicit Regularization via Mirror Descent","created":"2023-06-24","cited_by_count":14,"area":null},{"id":"2103.05524","title":"On the interplay between data structure and loss function in classification problems","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2302.02605","title":"Toward Large Kernel Models","created":"2023-02-06","cited_by_count":13,"area":null},{"id":"2307.08122","title":"Tangent Transformers for Composition, Privacy and Removal","created":"2023-07-16","cited_by_count":13,"area":null},{"id":"2503.10065","title":"Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild","created":"2025-03-13","cited_by_count":13,"area":null},{"id":"2307.07785","title":"The Interpolating Information Criterion for Overparameterized Models","created":"2023-07-15","cited_by_count":12,"area":null},{"id":"2203.03099","title":"Singular Value Perturbation and Deep Network Optimization","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2208.08112","title":"DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning","created":"2022-08-17","cited_by_count":11,"area":null},{"id":"2310.04357","title":"Asymptotically free sketched ridge ensembles: Risks, cross-validation, and tuning","created":"2023-10-06","cited_by_count":11,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2502.10691","title":"Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning","created":"2025-02-15","cited_by_count":11,"area":null},{"id":"2203.03443","title":"Generalization Through The Lens Of Leave-One-Out Error","created":"2022-03-07","cited_by_count":10,"area":null},{"id":"2510.27688","title":"Continuous Autoregressive Language Models","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2107.06665","title":"Disparity Between Batches as a Signal for Early Stopping","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2210.08709","title":"A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2210.10019","title":"Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation","created":"2022-10-18","cited_by_count":9,"area":null},{"id":"2302.06245","title":"Calibrating a Deep Neural Network with Its Predecessors","created":"2023-02-13","cited_by_count":9,"area":null},{"id":"2505.07812","title":"Continuous Visual Autoregressive Generation via Score Maximization","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2603.05002","title":"Non-Euclidean Gradient Descent Operates at the Edge of Stability","created":"2026-03-05","cited_by_count":9,"area":null},{"id":"2206.01399","title":"Generalization for multiclass classification with overparameterized linear models","created":"2022-06-03","cited_by_count":8,"area":null},{"id":"2401.01268","title":"$f$-Divergence Based Classification: Beyond the Use of Cross-Entropy","created":"2024-01-02","cited_by_count":8,"area":null},{"id":"2405.18906","title":"Language Generation with Strictly Proper Scoring Rules","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2410.00645","title":"LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2410.17020","title":"LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization","created":"2024-10-22","cited_by_count":8,"area":null},{"id":"2209.15208","title":"Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2109.14002","title":"slimTrain -- A Stochastic Approximation Method for Training Separable Deep Neural Networks","created":"2021-09-28","cited_by_count":6,"area":null},{"id":"2302.03952","title":"Cut your Losses with Squentropy","created":"2023-02-08","cited_by_count":6,"area":null},{"id":"2305.08813","title":"Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks","created":"2023-05-15","cited_by_count":6,"area":null},{"id":"2107.09957","title":"Memorization in Deep Neural Networks: Does the Loss Function matter?","created":"2021-07-21","cited_by_count":5,"area":null},{"id":"2205.03940","title":"Investigating Generalization by Controlling Normalized Margin","created":"2022-05-08","cited_by_count":5,"area":null},{"id":"2301.11797","title":"From Classification Accuracy to Proper Scoring Rules: Elicitability of Probabilistic Top List Predictions","created":"2023-01-27","cited_by_count":5,"area":null},{"id":"2310.07765","title":"Feature Learning and Generalization in Deep Networks with Orthogonal Weights","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2405.13922","title":"Towards Certification of Uncertainty Calibration under Adversarial Attacks","created":"2024-05-22","cited_by_count":5,"area":null},{"id":"2503.22725","title":"Uncertainty Weighted Gradients for Model Calibration","created":"2025-03-26","cited_by_count":5,"area":null},{"id":"2510.04606","title":"Closed-Form Last Layer Optimization","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2210.00346","title":"Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2303.07475","title":"General Loss Functions Lead to (Approximate) Interpolation in High Dimensions","created":"2023-03-13","cited_by_count":4,"area":null},{"id":"2304.13950","title":"Fairness Uncertainty Quantification: How certain are you that the model is fair?","created":"2023-04-27","cited_by_count":4,"area":null},{"id":"2406.02105","title":"Can Kernel Methods Explain How the Data Affects Neural Collapse?","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2207.07612","title":"Blessing of Nonconvexity in Deep Linear Models: Depth Flattens the Optimization Landscape Around the True Solution","created":"2022-07-15","cited_by_count":3,"area":null},{"id":"2305.02304","title":"New Equivalences Between Interpolation and SVMs: Kernels and Structured Features","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2308.00190","title":"Universal Majorization-Minimization Algorithms","created":"2023-07-31","cited_by_count":3,"area":null},{"id":"2310.17610","title":"A qualitative difference between gradient flows of convex functions in finite- and infinite-dimensional Hilbert spaces","created":"2023-10-26","cited_by_count":3,"area":null},{"id":"2403.09889","title":"Generalization of Scaled Deep ResNets in the Mean-Field Regime","created":"2024-03-14","cited_by_count":3,"area":null},{"id":"2411.16658","title":"Fast training of large kernel models with delayed projections","created":"2024-11-25","cited_by_count":3,"area":null},{"id":"2505.12245","title":"AFCL: Analytic Federated Continual Learning for Spatio-Temporal Invariance of Non-IID Data","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2112.09727","title":"Rank4Class: A Ranking Formulation for Multiclass Classification","created":"2021-12-17","cited_by_count":2,"area":null},{"id":"2407.11774","title":"Sharif-MGTD at SemEval-2024 Task 8: A Transformer-Based Approach to Detect Machine Generated Text","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2504.06805","title":"Robust Classification with Noisy Labels Based on Posterior Maximization","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2504.13548","title":"Beyond One-Hot Labels: Semantic Mixing for Model Calibration","created":"2025-04-18","cited_by_count":2,"area":null},{"id":"2505.08348","title":"Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2508.10732","title":"APFL: Analytic Personalized Federated Learning via Dual-Stream Least Squares","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2601.02543","title":"Normalized Conditional Mutual Information Surrogate Loss for Deep Neural Classifiers","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.12011","title":"Why Loss Re-weighting Works If You Stop Early: Training Dynamics of Unconstrained Features","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2102.06602","title":"Modeling Dynamic User Interests: A Neural Matrix Factorization Approach","created":"2021-02-12","cited_by_count":1,"area":null},{"id":"2104.10507","title":"On Sampling-Based Training Criteria for Neural Language Modeling","created":"2021-04-21","cited_by_count":1,"area":null},{"id":"2109.04875","title":"Neural Networks for Latent Budget Analysis of Compositional Data","created":"2021-09-10","cited_by_count":1,"area":null}],"next_cursor":"100"}