{"total":77,"rows":[{"id":"2511.00674","title":"Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?","created":"2025-11-01","cited_by_count":37,"area":null},{"id":"2605.20119","title":"Toto 2.0: Time Series Forecasting Enters the Scaling Era","created":"2026-05-19","cited_by_count":30,"area":null},{"id":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18,"area":null},{"id":"2603.09697","title":"Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning","created":"2026-03-10","cited_by_count":17,"area":null},{"id":"2603.28254","title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","created":"2026-03-30","cited_by_count":17,"area":null},{"id":"2604.09967","title":"Muon$^2$: Boosting Muon via Adaptive Second-Moment Preconditioning","created":"2026-04-11","cited_by_count":17,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2606.16899","title":"Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization","created":"2026-06-15","cited_by_count":16,"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":"2602.17080","title":"Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum","created":"2026-02-19","cited_by_count":14,"area":null},{"id":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2601.23261","title":"TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training","created":"2026-01-30","cited_by_count":6,"area":null},{"id":"2602.13498","title":"TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers","created":"2026-02-13","cited_by_count":6,"area":null},{"id":"2602.21545","title":"MUON+: Towards More Effective Muon via One Additional Normalization Step for LLM Pre-training","created":"2026-02-25","cited_by_count":6,"area":null},{"id":"2605.10797","title":"Muown: Row-Norm Control for Muon Optimization","created":"2026-05-11","cited_by_count":6,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2606.04662","title":"Why Muon Outperforms Adam: A Curvature Perspective","created":"2026-06-03","cited_by_count":6,"area":null},{"id":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2608.08888","title":"Full-bandwidth transformer","created":"2026-08-09","cited_by_count":5,"area":null},{"id":"2512.09678","title":"Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2602.06880","title":"Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2603.17970","title":"Beyond Muon: MUD (MomentUm Decorrelation) for Faster Transformer Training","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2605.22432","title":"AMUSE: Anytime Muon with Stable Gradient Evaluation","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2606.04058","title":"Spectral Scaling Laws of Muon","created":"2026-06-02","cited_by_count":4,"area":null},{"id":"2606.27715","title":"Aurora: A Leverage-Aware Spectral Optimizer","created":"2026-06-26","cited_by_count":4,"area":null},{"id":"2607.22444","title":"Hyperball May Not Be a Free Lunch","created":"2026-07-24","cited_by_count":4,"area":null},{"id":"2608.11612","title":"Dion3: Full-Stack Orthogonal Updates","created":"2026-08-12","cited_by_count":4,"area":null},{"id":"2602.01105","title":"OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\\ell_{\\infty}$ Implicit Biases","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2605.23061","title":"Anytime Training with Schedule-Free Spectral Optimization","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2606.23637","title":"Muown Implicitly Performs Angular Step-size Decay","created":"2026-06-22","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":"2603.00416","title":"MuonRec: Shifting the Optimizer Paradigm Beyond Adam in Scalable Generative Recommendation","created":"2026-02-28","cited_by_count":2,"area":null},{"id":"2603.10544","title":"SCORE: Replacing Layer Stacking with Contractive Recurrent Depth","created":"2026-03-11","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":"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":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.21803","title":"Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws","created":"2026-05-20","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":"2606.29176","title":"Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks","created":"2026-06-28","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":"2609.11655","title":"Musec: MomentUm SpEctral Clipping for Stable Muon-type Training","created":"2026-09-10","cited_by_count":2,"area":null},{"id":"2602.02522","title":"IMU-1: Sample-Efficient Pre-training of Small Language Models","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2605.11396","title":"MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.25395","title":"EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning Optimization","created":"2026-05-25","cited_by_count":1,"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":"2606.13867","title":"Muon$^p$: Muon with Fractional Spectral Powers","created":"2026-06-11","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":"2608.25990","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":"2609.21815","title":"Matrix AdaGrad: Row-wise and Column-wise Adaptive Subgradient Methods","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2601.14603","title":"Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.01845","title":"No Generation without Representation: Efficient Causal Protein Language Models Enable Zero-Shot Fitness Estimation","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2605.12491","title":"Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17806","title":"AMO: Operator-level Adaptive Muon Orthogonalization","created":"2026-05-18","cited_by_count":0,"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":"2605.27767","title":"UniMaia: Steering Chess Policies with Language for Human-like Play","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.14970","title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.30634","title":"One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.30813","title":"Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization","created":"2026-06-29","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":"2608.22994","title":"A Physical Response-and-Memory Model for Muon Optimization","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.26973","title":"Squeezing More from Limited Data with Recursive Transformers","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.28442","title":"Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining","created":"2026-08-28","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":"2609.13677","title":"Nonsmooth Optimization via Orthogonalized Momentum","created":"2026-09-12","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":"2609.35701","title":"MeqMuon: Matrix-Equilibrating Muon for LLM Pretraining","created":"2026-09-28","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":"2610.01395","title":"AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02705","title":"MuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model Heads","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.10965","title":"Spectrally Targeted Muon","created":"2026-10-07","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":"2610.16652","title":"IND-Eval: Aligning Evaluation and Simulation for Industrial Time Series Foundation Models","created":"2026-10-12","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}