{"total":41,"rows":[{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73,"area":null},{"id":"2307.09542","title":"Can Neural Network Memorization Be Localized?","created":"2023-07-18","cited_by_count":69,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2302.10911","title":"Revisiting Weighted Aggregation in Federated Learning with Neural Networks","created":"2023-02-14","cited_by_count":58,"area":null},{"id":"2307.03132","title":"T-MARS: Improving Visual Representations by Circumventing Text Feature Learning","created":"2023-07-06","cited_by_count":43,"area":null},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2106.13897","title":"Implicit Gradient Alignment in Distributed and Federated Learning","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2203.10036","title":"On the Generalization Mystery in Deep Learning","created":"2022-03-18","cited_by_count":25,"area":null},{"id":"2303.00586","title":"FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling","created":"2023-03-01","cited_by_count":11,"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":"2211.02077","title":"Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2102.06604","title":"Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2112.08798","title":"Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation","created":"2021-12-16","cited_by_count":7,"area":null},{"id":"2507.09937","title":"Memorization Sinks: Isolating Memorization during LLM Training","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2307.10718","title":"Differences Between Hard and Noisy-labeled Samples: An Empirical Study","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2406.02744","title":"DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2306.04072","title":"Exploring Simple, High Quality Out-of-Distribution Detection with L2 Normalization","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2401.08909","title":"Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2504.17474","title":"Enhanced Sample Selection with Confidence Tracking: Identifying Correctly Labeled yet Hard-to-Learn Samples in Noisy Data","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2211.16756","title":"Split-PU: Hardness-aware Training Strategy for Positive-Unlabeled Learning","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2212.04461","title":"Leveraging Unlabeled Data to Track Memorization","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2505.14512","title":"Just One Layer Norm Guarantees Stable Extrapolation","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2511.17378","title":"A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2505.15013","title":"Convergence of Adam in Deep ReLU Networks via Directional Complexity and Kakeya Bounds","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.15303","title":"Laplace Sample Information: Data Informativeness Through a Bayesian Lens","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.00024","title":"Generalization vs. Memorization in Autoregressive Deep Learning: Or, Examining Temporal Decay of Gradient Coherence","created":"2025-08-18","cited_by_count":1,"area":null},{"id":"2510.25480","title":"Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2607.24887","title":"Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2111.01166","title":"Dynamics of Local Elasticity During Training of Neural Nets","created":"2021-11-01","cited_by_count":0,"area":null},{"id":"2203.08174","title":"Towards understanding deep learning with the natural clustering prior","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2305.12238","title":"Low-Entropy Latent Variables Hurt Out-of-Distribution Performance","created":"2023-05-20","cited_by_count":0,"area":null},{"id":"2403.00574","title":"Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2601.20172","title":"Loss Landscape Geometry of Partial Differential Equation Emulators: Or, Symmetry Learning via Gradient Alignment","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2606.25004","title":"Certification of Machine Learning Models via Directional Sharpness","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.28123","title":"Dangerous Liaisons of Convex Learning and Non-Affine Aggregation","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.15483","title":"Measuring Structured Predictability in Neural Training Dynamics: A Cross-Regime Study","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2610.00436","title":"Every Batch Is Its Own Validation Set: Leave-One-Out Gradient Matching for Online Data Selection in LLM Fine-Tuning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01425","title":"Why Does Train-Validation Separation Emerge? Update-Pressure Density Dynamics in Pretrained Backbones","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}