{"total":20,"rows":[{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2503.10537","title":"Structured Preconditioners in Adaptive Optimization: A Unified Analysis","created":"2025-03-13","cited_by_count":33,"area":null},{"id":"2506.12543","title":"Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling","created":"2025-06-14","cited_by_count":15,"area":null},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10,"area":null},{"id":"2505.11840","title":"On the $O(\\frac{\\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\\ell_1$ Norm","created":"2025-05-17","cited_by_count":8,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2510.14717","title":"Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2511.20584","title":"A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2512.00763","title":"Provable Benefit of SignGD: A Minimal Model Under Heavy-Tailed Class Imbalance","created":"2025-11-30","cited_by_count":5,"area":null},{"id":"2603.09581","title":"Towards Understanding Adam Convergence on Highly Degenerate Polynomials","created":"2026-03-10","cited_by_count":4,"area":null},{"id":"2510.23804","title":"How do simple rotations affect the implicit bias of Adam?","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2510.26303","title":"Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2602.03515","title":"Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2605.06615","title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\\ell_1$-norm Lower Bounds","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2608.22129","title":"Blockwise Stabilized Adaptive Cubic Regularization with Subsolvers via Recurrence","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2601.22614","title":"Stabilizing Transformer Training Through Consensus","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.11059","title":"Uniform Scaling Limits in AdamW-Trained Transformers","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2608.05136","title":"The Loss Does Not See the Basis, but Adam Does","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2610.17285","title":"Which Geometry on Which Layer? Measured Sign-Spectral Assignment in Mixed-Optimizer Training","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}