{"total":131,"rows":[{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84,"area":null},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2410.01623","title":"Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2407.07972","title":"Deconstructing What Makes a Good Optimizer for Language Models","created":"2024-07-10","cited_by_count":41,"area":null},{"id":"2502.04664","title":"Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data","created":"2025-02-07","cited_by_count":41,"area":null},{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40,"area":null},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2412.13795","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","created":"2024-12-18","cited_by_count":37,"area":null},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30,"area":null},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"area":null},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","cited_by_count":28,"area":null},{"id":"2505.19227","title":"Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf's Law","created":"2025-05-25","cited_by_count":24,"area":null},{"id":"2410.08198","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity","created":"2024-10-10","cited_by_count":23,"area":null},{"id":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2505.24749","title":"SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training","created":"2025-05-30","cited_by_count":19,"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":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16,"area":null},{"id":"2510.27403","title":"FedMuon: Accelerating Federated Learning with Matrix Orthogonalization","created":"2025-10-31","cited_by_count":16,"area":null},{"id":"2510.27486","title":"FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models","created":"2025-10-31","cited_by_count":15,"area":null},{"id":"2511.03634","title":"nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN","created":"2025-11-05","cited_by_count":15,"area":null},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14,"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":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2506.16659","title":"Memory-Efficient LLM Pretraining via Minimalist Optimizer Design","created":"2025-06-20","cited_by_count":13,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"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":"2410.19964","title":"Understanding Adam Requires Better Rotation Dependent Assumptions","created":"2024-10-25","cited_by_count":11,"area":null},{"id":"2411.01803","title":"Gradient Methods with Online Scaling","created":"2024-11-04","cited_by_count":11,"area":null},{"id":"2601.21750","title":"FISMO: Fisher-Structured Momentum-Orthogonalized Optimizer","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2411.07837","title":"FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training","created":"2024-11-12","cited_by_count":10,"area":null},{"id":"2410.10986","title":"What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2502.06742","title":"Gradient Multi-Normalization for Stateless and Scalable LLM Training","created":"2025-02-10","cited_by_count":9,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2602.04669","title":"Delving into Muon and Beyond: Deep Analysis and Extensions","created":"2026-02-04","cited_by_count":9,"area":null},{"id":"2412.11768","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","created":"2024-12-16","cited_by_count":8,"area":null},{"id":"2412.19820","title":"GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection","created":"2024-12-15","cited_by_count":8,"area":null},{"id":"2501.12243","title":"FOCUS: First Order Concentrated Updating Scheme","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7,"area":null},{"id":"2409.18872","title":"Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networks","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2502.17055","title":"GradientStabilizer:Fix the Norm, Not the Gradient","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2505.16363","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2603.16731","title":"Understanding Quantization of Optimizer States in LLM Pre-training: Dynamics of State Staleness and Effectiveness of State Resets","created":"2026-03-17","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":"2502.11229","title":"Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent","created":"2025-02-16","cited_by_count":5,"area":null},{"id":"2502.19571","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2505.00347","title":"Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics","created":"2025-05-01","cited_by_count":5,"area":null},{"id":"2505.22922","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2505.23737","title":"On the Convergence Analysis of Muon","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2507.08472","title":"Pre-Training LLMs on a budget: A comparison of three optimizers","created":"2025-07-11","cited_by_count":5,"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":"2602.23349","title":"FlashOptim: Optimizers for Memory-Efficient Training","created":"2026-02-26","cited_by_count":5,"area":null},{"id":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2407.19342","title":"Parameter-Efficient Fine-Tuning via Circular Convolution","created":"2024-07-27","cited_by_count":4,"area":null},{"id":"2509.05213","title":"An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2510.01377","title":"DeMuon: A Decentralized Muon for Matrix Optimization over Graphs","created":"2025-10-01","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":"2604.09258","title":"Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2503.01843","title":"When Can You Get Away with Low Memory Adam?","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2505.11081","title":"ShiQ: Bringing back Bellman to LLMs","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2505.23081","title":"Gradient Methods with Online Scaling Part I. Theoretical Foundations","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2507.08963","title":"Stochastic Approximation with Block Coordinate Optimal Stepsizes","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2510.00419","title":"Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2510.09103","title":"AdaPM: a Partial Momentum Algorithm for LLM Training","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2510.14009","title":"Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2510.25244","title":"BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training","created":"2025-10-29","cited_by_count":3,"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":"2605.22297","title":"One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2411.07120","title":"Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2501.19099","title":"Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2502.10784","title":"Preconditioned Inexact Stochastic ADMM for Deep Model","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2509.18396","title":"Development of Deep Learning Optimizers: Approaches, Concepts, and Update Rules","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2511.00056","title":"MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2602.01212","title":"SimpleGPT: Improving GPT via A Simple Normalization Strategy","created":"2026-02-01","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":"2602.09169","title":"Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2605.00650","title":"AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2606.02365","title":"FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo","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":"2606.22932","title":"FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2501.07237","title":"GWT: Scalable Optimizer State Compression for Large Language Model Training","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2508.06309","title":"Matrix-Driven Identification and Reconstruction of LLM Weight Homology","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2509.22418","title":"Partial Parameter Updates for Efficient Distributed Training","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.01878","title":"Geometrically Principled Randomized Optimization for Efficient LLM Training","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2511.16084","title":"SpectralTrain: A Universal Framework for Hyperspectral Image Classification","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.07112","title":"FOAM: Blocked State Folding for Memory-Efficient LLM Training","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2601.22095","title":"GeoNorm: Unify Pre-Norm and Post-Norm with Geodesic Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.00545","title":"Depth, Not Data: An Analysis of Hessian Spectral Bifurcation","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.07632","title":"Scalable Mean-Field Variational Inference via Preconditioned Primal-Dual Optimization","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.23111","title":"PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.06120","title":"Dynamic Momentum Recalibration in Online Gradient Learning","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2604.02505","title":"Optimal Projection-Free Adaptive SGD for Matrix Optimization","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2605.04711","title":"Budget-aware Auto Optimizer Configurator","created":"2026-05-06","cited_by_count":1,"area":null}],"next_cursor":"100"}