{"total":32,"rows":[{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166,"area":null},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"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":"2207.02628","title":"The alignment property of SGD noise and how it helps select flat minima: A stability analysis","created":"2022-07-06","cited_by_count":64,"area":null},{"id":"2107.14153","title":"Semi-Supervised Active Learning with Temporal Output Discrepancy","created":"2021-07-29","cited_by_count":50,"area":null},{"id":"2305.17490","title":"The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent","created":"2023-05-27","cited_by_count":44,"area":null},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36,"area":null},{"id":"2203.10036","title":"On the Generalization Mystery in Deep Learning","created":"2022-03-18","cited_by_count":25,"area":null},{"id":"2305.16427","title":"Neural (Tangent Kernel) Collapse","created":"2023-05-25","cited_by_count":18,"area":null},{"id":"2210.06788","title":"TiDAL: Learning Training Dynamics for Active Learning","created":"2022-10-13","cited_by_count":11,"area":null},{"id":"2310.01365","title":"Elephant Neural Networks: Born to Be a Continual Learner","created":"2023-10-02","cited_by_count":10,"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":"2107.06665","title":"Disparity Between Batches as a Signal for Early Stopping","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2110.05960","title":"Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations","created":"2021-10-11","cited_by_count":8,"area":null},{"id":"2206.01515","title":"Understanding Deep Learning via Decision Boundary","created":"2022-06-03","cited_by_count":7,"area":null},{"id":"2310.17163","title":"Low-Dimensional Gradient Helps Out-of-Distribution Detection","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2210.11452","title":"Global Convergence of SGD On Two Layer Neural Nets","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2409.09626","title":"Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics","created":"2024-09-15","cited_by_count":5,"area":null},{"id":"2205.12642","title":"On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2112.09741","title":"Envisioning Future Deep Learning Theories: Some Basic Concepts and Characteristics","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2309.09258","title":"Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2310.05105","title":"How Graph Neural Networks Learn: Lessons from Training Dynamics","created":"2023-10-08","cited_by_count":3,"area":null},{"id":"2507.14559","title":"LEAD: Exploring Logit Space Evolution for Model Selection","created":"2025-07-19","cited_by_count":3,"area":null},{"id":"2212.10613","title":"Temporal Output Discrepancy for Loss Estimation-based Active Learning","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2401.02904","title":"Class-wise Generalization Error: an Information-Theoretic Analysis","created":"2024-01-05","cited_by_count":2,"area":null},{"id":"2505.16017","title":"GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2106.10653","title":"Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples","created":"2021-06-20","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":"2111.01166","title":"Dynamics of Local Elasticity During Training of Neural Nets","created":"2021-11-01","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":"2609.23260","title":"Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning","created":"2026-09-20","cited_by_count":0,"area":null}],"next_cursor":null}