{"total":17,"rows":[{"id":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18,"area":null},{"id":"2603.20527","title":"RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization","created":"2026-03-20","cited_by_count":15,"area":null},{"id":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2602.19271","title":"Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data","created":"2026-02-22","cited_by_count":4,"area":null},{"id":"2605.17471","title":"WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2510.13680","title":"Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise","created":"2025-10-15","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":"2605.16165","title":"Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.11316","title":"Error whitening: Why Gauss-Newton outperforms Newton","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2608.09763","title":"Second-Order Muon Done Right: A Principled Marriage of Spectral Geometry and Curvature","created":"2026-08-10","cited_by_count":1,"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":"2511.03972","title":"Non-Asymptotic Optimization and Generalization Bounds for Stochastic Gauss-Newton in Overparameterized Models","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2604.11639","title":"Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2608.16760","title":"On the Principles Behind Neural Network Optimizers","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.02966","title":"Physics-Informed Neural Network Surrogate for Oxygen Vacancy Dynamics in epitaxial $\\mathrm{SrTiO_3}$ on Si memristors via Dynamic Spectral Optimization","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.33016","title":"Relative Generalization Invariance of LLM Pretraining","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36600","title":"Second-Moment Stochastic Approximation Methods","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}