{"total":16,"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":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101,"area":null},{"id":"2105.13462","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","created":"2021-05-27","cited_by_count":63,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2204.11326","title":"Beyond the Quadratic Approximation: the Multiscale Structure of Neural Network Loss Landscapes","created":"2022-04-24","cited_by_count":43,"area":null},{"id":"2210.04860","title":"Second-order regression models exhibit progressive sharpening to the edge of stability","created":"2022-10-10","cited_by_count":40,"area":null},{"id":"2302.00543","title":"DoCoFL: Downlink Compression for Cross-Device Federated Learning","created":"2023-02-01","cited_by_count":28,"area":null},{"id":"2304.06947","title":"TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training","created":"2023-04-14","cited_by_count":27,"area":null},{"id":"2103.01338","title":"Acceleration via Fractal Learning Rate Schedules","created":"2021-03-01","cited_by_count":13,"area":null},{"id":"2407.19234","title":"Ordered Momentum for Asynchronous SGD","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2304.04172","title":"$\\mu^2$-SGD: Stable Stochastic Optimization via a Double Momentum Mechanism","created":"2023-04-09","cited_by_count":4,"area":null},{"id":"2306.10598","title":"DropCompute: simple and more robust distributed synchronous training via compute variance reduction","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2312.00209","title":"On the Interplay Between Stepsize Tuning and Progressive Sharpening","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2506.19645","title":"Tensor-Parallelism with Partially Synchronized Activations","created":"2025-06-24","cited_by_count":4,"area":null},{"id":"2509.02970","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","created":"2025-09-03","cited_by_count":3,"area":null},{"id":"2605.02043","title":"Bringing Order to Asynchronous SGD: Towards Optimality under Data-Dependent Delays with Momentum","created":"2026-05-03","cited_by_count":0,"area":null}],"next_cursor":null}