{"total":20,"rows":[{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2305.20057","title":"Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance","created":"2023-05-31","cited_by_count":36,"area":null},{"id":"2302.05933","title":"Generalization Ability of Wide Neural Networks on $\\mathbb{R}$","created":"2023-02-12","cited_by_count":30,"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":"2305.16891","title":"Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2305.02247","title":"Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2307.03357","title":"Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms","created":"2023-07-07","cited_by_count":3,"area":null},{"id":"2501.12737","title":"Stability and Generalization of Quantum Neural Networks","created":"2025-01-22","cited_by_count":3,"area":null},{"id":"2510.02779","title":"Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification","created":"2025-10-03","cited_by_count":3,"area":null},{"id":"2505.19087","title":"Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2507.23136","title":"Observational Multiplicity","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2211.03570","title":"Do highly over-parameterized neural networks generalize since bad solutions are rare?","created":"2022-11-07","cited_by_count":1,"area":null},{"id":"2410.01969","title":"Which Algorithms Have Tight Generalization Bounds?","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2601.22409","title":"Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2308.09430","title":"Towards Understanding the Generalizability of Delayed Stochastic Gradient Descent","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2409.01074","title":"Bootstrap SGD: Algorithmic Stability and Robustness","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2410.16868","title":"Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2504.01875","title":"AYLA: Architecting a loss landscape in shallow neural networks to accelerate feature recovery","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2606.06764","title":"Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.06772","title":"Minimax-Optimal Generalization Bounds for Smooth Deep Neural Networks Trained by (Stochastic) Gradient Descent","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}