{"list":"other","total":65,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"2306.06101","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","created":"2023-06-09","cited_by_count":133},{"id":"1712.07628","title":"Improving Generalization Performance by Switching from Adam to SGD","created":"2017-12-20","cited_by_count":125},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114},{"id":"2509.02046","title":"Fantastic Pretraining Optimizers and Where to Find Them","created":"2025-09-02","cited_by_count":100},{"id":"1806.06763","title":"Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks","created":"2018-06-18","cited_by_count":90},{"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":"1810.06801","title":"Quasi-hyperbolic momentum and Adam for deep learning","created":"2018-10-16","cited_by_count":48},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47},{"id":"2210.01620","title":"SAM as an Optimal Relaxation of Bayes","created":"2022-10-04","cited_by_count":41},{"id":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38},{"id":"1804.00325","title":"Aggregated Momentum: Stability Through Passive Damping","created":"2018-04-01","cited_by_count":36},{"id":"2601.08393","title":"Controlled LLM Training on Spectral Sphere","created":"2026-01-13","cited_by_count":31},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","cited_by_count":28},{"id":"2509.02981","title":"AdaGrad Meets Muon: Adaptive Stepsizes for Orthogonal Updates","created":"2025-09-03","cited_by_count":23},{"id":"2106.13731","title":"Ranger21: a synergistic deep learning optimizer","created":"2021-06-25","cited_by_count":22},{"id":"2506.02285","title":"Why Gradients Rapidly Increase Near the End of Training","created":"2025-06-02","cited_by_count":22},{"id":"2603.20527","title":"RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization","created":"2026-03-20","cited_by_count":15},{"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},{"id":"1910.12249","title":"An Adaptive and Momental Bound Method for Stochastic Learning","created":"2019-10-27","cited_by_count":12},{"id":"2006.08217","title":"AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights","created":"2020-06-15","cited_by_count":10},{"id":"2502.02431","title":"Connections between Schedule-Free Optimizers, AdEMAMix, and Accelerated SGD Variants","created":"2025-02-04","cited_by_count":10},{"id":"2504.02507","title":"ZClip: Adaptive Spike Mitigation for LLM Pre-Training","created":"2025-04-03","cited_by_count":10},{"id":"1905.11286","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","created":"2019-05-27","cited_by_count":9},{"id":"2211.04422","title":"Black Box Lie Group Preconditioners for SGD","created":"2022-11-08","cited_by_count":9},{"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":"2412.11768","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","created":"2024-12-16","cited_by_count":8},{"id":"2501.12243","title":"FOCUS: First Order Concentrated Updating Scheme","created":"2025-01-21","cited_by_count":8},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7},{"id":"2502.11034","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","created":"2025-02-16","cited_by_count":6},{"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},{"id":"2507.08472","title":"Pre-Training LLMs on a budget: A comparison of three optimizers","created":"2025-07-11","cited_by_count":5},{"id":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","cited_by_count":5},{"id":"2412.17107","title":"Grams: Gradient Descent with Adaptive Momentum Scaling","created":"2024-12-22","cited_by_count":4},{"id":"2110.10828","title":"AdamD: Improved bias-correction in Adam","created":"2021-10-20","cited_by_count":3},{"id":"2410.06373","title":"Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning","created":"2024-10-08","cited_by_count":3},{"id":"2602.23057","title":"Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention","created":"2026-02-26","cited_by_count":3},{"id":"2604.12968","title":"Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations","created":"2026-04-14","cited_by_count":3},{"id":"2412.18790","title":"Torque-Aware Momentum","created":"2024-12-25","cited_by_count":2},{"id":"2412.20302","title":"EXAdam: The Power of Adaptive Cross-Moments","created":"2024-12-29","cited_by_count":2},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2},{"id":"2506.04487","title":"OrthoGrad Improves Neural Calibration","created":"2025-06-04","cited_by_count":2},{"id":"2509.18396","title":"Development of Deep Learning Optimizers: Approaches, Concepts, and Update Rules","created":"2025-09-22","cited_by_count":2},{"id":"2605.09176","title":"Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers","created":"2026-05-09","cited_by_count":2},{"id":"2101.09192","title":"Gravity Optimizer: a Kinematic Approach on Optimization in Deep Learning","created":"2021-01-22","cited_by_count":1},{"id":"2508.18258","title":"ANO : Faster is Better in Noisy Landscape","created":"2025-08-25","cited_by_count":1}],"next_cursor":null}