{"list":"other","total":52,"rows":[{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170},{"id":"2405.15682","title":"The Road Less Scheduled","created":"2024-05-24","cited_by_count":163},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137},{"id":"2509.02046","title":"Fantastic Pretraining Optimizers and Where to Find Them","created":"2025-09-02","cited_by_count":100},{"id":"2510.05491","title":"NorMuon: Making Muon more efficient and scalable","created":"2025-10-07","cited_by_count":84},{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68},{"id":"2509.01440","title":"Benchmarking Optimizers for Large Language Model Pretraining","created":"2025-09-01","cited_by_count":68},{"id":"2507.11005","title":"AdaMuon: Adaptive Muon Optimizer","created":"2025-07-15","cited_by_count":67},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64},{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47},{"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},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38},{"id":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30},{"id":"2408.13359","title":"Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler","created":"2024-08-23","cited_by_count":28},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","cited_by_count":28},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20},{"id":"2411.02853","title":"ADOPT: Modified Adam Can Converge with Any $\\beta_2$ with the Optimal Rate","created":"2024-11-05","cited_by_count":18},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18},{"id":"2603.09697","title":"Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning","created":"2026-03-10","cited_by_count":17},{"id":"2603.28254","title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","created":"2026-03-30","cited_by_count":17},{"id":"2510.25000","title":"What Really Matters in Matrix-Whitening Optimizers?","created":"2025-10-28","cited_by_count":16},{"id":"2606.16899","title":"Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization","created":"2026-06-15","cited_by_count":16},{"id":"2504.20437","title":"GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection","created":"2025-04-29","cited_by_count":14},{"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},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13},{"id":"2603.16127","title":"Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning","created":"2026-03-17","cited_by_count":13},{"id":"2509.23106","title":"Effective Quantization of Muon Optimizer States","created":"2025-09-27","cited_by_count":11},{"id":"2605.18106","title":"Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers","created":"2026-05-18","cited_by_count":11},{"id":"2411.07837","title":"FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training","created":"2024-11-12","cited_by_count":10},{"id":"2502.07752","title":"Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension","created":"2025-02-11","cited_by_count":9},{"id":"2605.19095","title":"ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models","created":"2026-05-18","cited_by_count":7},{"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},{"id":"2505.00347","title":"Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics","created":"2025-05-01","cited_by_count":5},{"id":"2601.22101","title":"ECO: Quantized Training without Full-Precision Master Weights","created":"2026-01-29","cited_by_count":5},{"id":"2604.06836","title":"STQuant: Spatio-Temporal Adaptive Framework for Optimizer Quantization in Large Multimodal Model Training","created":"2026-04-08","cited_by_count":4},{"id":"2605.31371","title":"Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling","created":"2026-05-29","cited_by_count":4},{"id":"2503.01843","title":"When Can You Get Away with Low Memory Adam?","created":"2025-03-03","cited_by_count":3},{"id":"2605.23061","title":"Anytime Training with Schedule-Free Spectral Optimization","created":"2026-05-21","cited_by_count":3},{"id":"2606.23637","title":"Muown Implicitly Performs Angular Step-size Decay","created":"2026-06-22","cited_by_count":3},{"id":"2605.29547","title":"Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization","created":"2026-05-28","cited_by_count":1}],"next_cursor":null}