{"total":426,"rows":[{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265,"area":null},{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193,"area":null},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"area":null},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2505.16932","title":"The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm","created":"2025-05-22","cited_by_count":110,"area":null},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108,"area":null},{"id":"2503.12645","title":"Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization","created":"2025-03-16","cited_by_count":92,"area":null},{"id":"2106.12372","title":"Real-time Neural Radiance Caching for Path Tracing","created":"2021-06-23","cited_by_count":91,"area":null},{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86,"area":"deeprl"},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86,"area":null},{"id":"2302.12022","title":"DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule","created":"2023-02-08","cited_by_count":85,"area":null},{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84,"area":null},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82,"area":null},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"area":null},{"id":"2410.21265","title":"Modular Duality in Deep Learning","created":"2024-10-28","cited_by_count":77,"area":null},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"area":null},{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68,"area":null},{"id":"2507.11005","title":"AdaMuon: Adaptive Muon Optimizer","created":"2025-07-15","cited_by_count":67,"area":null},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56,"area":null},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47,"area":null},{"id":"2302.10322","title":"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","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":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41,"area":null},{"id":"2507.07101","title":"Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful","created":"2025-07-09","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":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"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":"2601.19156","title":"Convergence of Muon with Newton-Schulz","created":"2026-01-27","cited_by_count":36,"area":null},{"id":"2205.15242","title":"Re-parameterizing Your Optimizers rather than Architectures","created":"2022-05-30","cited_by_count":35,"area":null},{"id":"2502.15938","title":"Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs","created":"2025-02-21","cited_by_count":35,"area":null},{"id":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35,"area":null},{"id":"2209.05310","title":"On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models","created":"2022-09-12","cited_by_count":34,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2503.10537","title":"Structured Preconditioners in Adaptive Optimization: A Unified Analysis","created":"2025-03-13","cited_by_count":33,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2203.11860","title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","created":"2022-03-22","cited_by_count":32,"area":null},{"id":"2410.20625","title":"LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization","created":"2024-10-27","cited_by_count":32,"area":null},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31,"area":null},{"id":"2601.08393","title":"Controlled LLM Training on Spectral Sphere","created":"2026-01-13","cited_by_count":31,"area":"moe"},{"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":"2601.13474","title":"Preconditioning Benefits of Spectral Orthogonalization in Muon","created":"2026-01-20","cited_by_count":30,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2507.01598","title":"Convergence Bound and Critical Batch Size of Muon Optimizer","created":"2025-07-02","cited_by_count":28,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2205.10637","title":"Symmetry Teleportation for Accelerated Optimization","created":"2022-05-21","cited_by_count":25,"area":null},{"id":"2106.02925","title":"Tensor Normal Training for Deep Learning Models","created":"2021-06-05","cited_by_count":24,"area":null},{"id":"2110.06399","title":"Dynamic Inference with Neural Interpreters","created":"2021-10-12","cited_by_count":24,"area":null},{"id":"2211.14133","title":"PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","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":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23,"area":"deeprl"},{"id":"2509.02981","title":"AdaGrad Meets Muon: Adaptive Stepsizes for Orthogonal Updates","created":"2025-09-03","cited_by_count":23,"area":null},{"id":"2509.14562","title":"LiMuon: Light and Fast Muon Optimizer for Large Models","created":"2025-09-18","cited_by_count":22,"area":null},{"id":"2305.04684","title":"ASDL: A Unified Interface for Gradient Preconditioning in PyTorch","created":"2023-05-08","cited_by_count":21,"area":null},{"id":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"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":"2405.15593","title":"MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence","created":"2024-05-24","cited_by_count":19,"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":"2507.02608","title":"Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation","created":"2025-07-03","cited_by_count":19,"area":"diffusion"},{"id":"2510.22980","title":"How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data","created":"2025-10-27","cited_by_count":19,"area":null},{"id":"2212.00309","title":"Differentially Private Adaptive Optimization with Delayed Preconditioners","created":"2022-12-01","cited_by_count":18,"area":null},{"id":"2405.12807","title":"FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2405.18144","title":"4-bit Shampoo for Memory-Efficient Network Training","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2410.22069","title":"Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks","created":"2024-10-29","cited_by_count":18,"area":null},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2509.11983","title":"Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training","created":"2025-09-15","cited_by_count":18,"area":null},{"id":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18,"area":null},{"id":"2302.03764","title":"Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2510.09378","title":"The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton","created":"2025-10-10","cited_by_count":17,"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":"2402.04553","title":"Curvature-Informed SGD via General Purpose Lie-Group Preconditioners","created":"2024-02-07","cited_by_count":16,"area":null},{"id":"2509.03378","title":"Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization","created":"2025-09-03","cited_by_count":16,"area":null},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16,"area":null},{"id":"2106.06199","title":"LocoProp: Enhancing BackProp via Local Loss Optimization","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"area":null},{"id":"2406.06420","title":"An Improved Empirical Fisher Approximation for Natural Gradient Descent","created":"2024-06-10","cited_by_count":15,"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":"2404.07946","title":"Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon","created":"2024-03-14","cited_by_count":14,"area":"diffusion"},{"id":"2405.16397","title":"AdaFisher: Adaptive Second Order Optimization via Fisher Information","created":"2024-05-26","cited_by_count":14,"area":null},{"id":"2602.08232","title":"Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization","created":"2026-02-09","cited_by_count":14,"area":null},{"id":"2605.11181","title":"Muon is Not That Special: Random or Inverted Spectra Work Just as Well","created":"2026-05-11","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":"2506.19697","title":"Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models","created":"2025-06-24","cited_by_count":13,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2506.23803","title":"SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration","created":"2025-06-30","cited_by_count":12,"area":null},{"id":"2603.09952","title":"On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer","created":"2026-03-10","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":"2109.14158","title":"Second-Order Neural ODE Optimizer","created":"2021-09-29","cited_by_count":11,"area":null}],"next_cursor":"100"}