{"total":15,"rows":[{"id":"2606.27715","title":"Aurora: A Leverage-Aware Spectral Optimizer","created":"2026-06-26","cited_by_count":4,"area":null},{"id":"2605.07067","title":"PolarAdamW: Disentangling Spectral Control and Schur Gauge-Equivariance in Matrix Optimisation","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2606.01850","title":"Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.17526","title":"MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2606.27216","title":"Hierarchical Muon: Tiled Newton-Schulz Updates for Efficient Muon Optimization","created":"2026-06-25","cited_by_count":2,"area":null},{"id":"2606.01720","title":"A Note on Stability for Orthogonalized Matrix Momentum with Client Sampling","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2607.14536","title":"Muse: Representation Geometry of Muon Beyond Normalized Momentum","created":"2026-07-16","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":"2605.19781","title":"From SGD to Muon: Adaptive Optimization via Schatten-p Norms","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.28557","title":"Blog: Survey of Optimizers","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.36692","title":"Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39114","title":"The Row Normalization Puzzle in Muon","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.10975","title":"Optimizing Large Language Models with Chained LMOs","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11309","title":"From Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}