{"total":17,"rows":[{"id":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2605.09552","title":"Phases of Muon: When Muon Eclipses SignSGD","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2606.27153","title":"DMuon: Efficient Distributed Muon Training with Near-Adam Overhead","created":"2026-06-25","cited_by_count":3,"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":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2607.17620","title":"PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2606.06418","title":"Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.15702","title":"Schattor: Schatten-family methods for deep learning optimization","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2608.05088","title":"MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning","created":"2026-08-05","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":"2608.25990","title":"Spectral Allocation: Why Muon Outperforms Adam, and How to Improve Muon","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2609.07597","title":"Beyond the Matrix Sign: Quadratic Spectral Descent","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2605.05284","title":"Direct From Darwin: Deriving Advanced Optimizers From Evolutionary First Principles","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2608.19491","title":"Activation-Keyed Momentum: An Anisotropic Momentum Update via the Delta Rule","created":"2026-08-19","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},{"id":"2610.03222","title":"Near-Optimal Convex Optimization with Lazy Second-Order Oracles","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.09040","title":"ORACLE: Optimizer-Relative Alignment for Constrained LEarning","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}