{"total":571,"rows":[{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"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":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"area":null},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141,"area":null},{"id":"2104.02151","title":"Distributed Learning in Wireless Networks: Recent Progress and Future Challenges","created":"2021-04-05","cited_by_count":129,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115,"area":null},{"id":"2304.13960","title":"Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be","created":"2023-04-27","cited_by_count":114,"area":null},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109,"area":null},{"id":"2308.08165","title":"Stochastic Controlled Averaging for Federated Learning with Communication Compression","created":"2023-08-16","cited_by_count":101,"area":null},{"id":"2111.12444","title":"Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications","created":"2021-11-24","cited_by_count":97,"area":null},{"id":"2206.07136","title":"Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger","created":"2022-06-14","cited_by_count":88,"area":null},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86,"area":null},{"id":"2201.08135","title":"Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges","created":"2022-01-20","cited_by_count":84,"area":null},{"id":"2208.11195","title":"Robustness to Unbounded Smoothness of Generalized SignSGD","created":"2022-08-23","cited_by_count":81,"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":"2102.01854","title":"Provably Secure Federated Learning against Malicious Clients","created":"2021-02-03","cited_by_count":63,"area":null},{"id":"2206.07638","title":"Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays","created":"2022-06-15","cited_by_count":63,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"area":null},{"id":"2404.04454","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","created":"2024-04-05","cited_by_count":58,"area":null},{"id":"2503.20762","title":"ASGO: Adaptive Structured Gradient Optimization","created":"2025-03-26","cited_by_count":57,"area":null},{"id":"2107.11621","title":"FedLab: A Flexible Federated Learning Framework","created":"2021-07-24","cited_by_count":55,"area":null},{"id":"2108.08842","title":"EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning","created":"2021-08-19","cited_by_count":55,"area":null},{"id":"2205.02719","title":"Communication-Efficient Adaptive Federated Learning","created":"2022-05-05","cited_by_count":55,"area":null},{"id":"2306.00204","title":"Toward Understanding Why Adam Converges Faster Than SGD for Transformers","created":"2023-05-31","cited_by_count":53,"area":null},{"id":"2101.12704","title":"Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis","created":"2021-01-29","cited_by_count":51,"area":null},{"id":"2310.05898","title":"Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts","created":"2023-10-09","cited_by_count":51,"area":null},{"id":"2103.17150","title":"Federated Learning: A Signal Processing Perspective","created":"2021-03-31","cited_by_count":49,"area":null},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2404.06448","title":"Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2024-04-09","cited_by_count":49,"area":null},{"id":"2410.13849","title":"From Gradient Clipping to Normalization for Heavy Tailed SGD","created":"2024-10-17","cited_by_count":49,"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":"2102.08098","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","created":"2021-02-16","cited_by_count":44,"area":null},{"id":"2403.07362","title":"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning","created":"2024-03-12","cited_by_count":44,"area":"safety"},{"id":"2511.13653","title":"Weight-sparse transformers have interpretable circuits","created":"2025-11-17","cited_by_count":44,"area":"mechinterp"},{"id":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41,"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":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40,"area":null},{"id":"2203.03761","title":"The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning","created":"2022-03-07","cited_by_count":39,"area":null},{"id":"2206.04055","title":"Gradient Obfuscation Gives a False Sense of Security in Federated Learning","created":"2022-06-08","cited_by_count":39,"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":"2206.08330","title":"Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data","created":"2022-06-16","cited_by_count":36,"area":null},{"id":"2406.10650","title":"The Implicit Bias of Adam on Separable Data","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2208.10888","title":"Joint Privacy Enhancement and Quantization in Federated Learning","created":"2022-08-23","cited_by_count":35,"area":null},{"id":"2202.07178","title":"Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy","created":"2022-02-15","cited_by_count":33,"area":null},{"id":"2206.03665","title":"Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression","created":"2022-06-08","cited_by_count":33,"area":null},{"id":"2209.15328","title":"Sparse Random Networks for Communication-Efficient Federated Learning","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2103.11109","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2204.01273","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","created":"2022-04-04","cited_by_count":31,"area":null},{"id":"2109.05872","title":"Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering","created":"2021-09-13","cited_by_count":30,"area":null},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30,"area":null},{"id":"2210.10880","title":"Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning","created":"2022-10-19","cited_by_count":30,"area":null},{"id":"2101.11075","title":"Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization","created":"2021-01-26","cited_by_count":28,"area":null},{"id":"2302.00543","title":"DoCoFL: Downlink Compression for Cross-Device Federated Learning","created":"2023-02-01","cited_by_count":28,"area":null},{"id":"2102.01593","title":"FEDZIP: A Compression Framework for Communication-Efficient Federated Learning","created":"2021-02-02","cited_by_count":27,"area":null},{"id":"2110.05323","title":"ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training","created":"2021-10-11","cited_by_count":27,"area":null},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2101.08837","title":"Time-Correlated Sparsification for Communication-Efficient Federated Learning","created":"2021-01-21","cited_by_count":26,"area":null},{"id":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26,"area":null},{"id":"2108.09513","title":"A Hard Label Black-box Adversarial Attack Against Graph Neural Networks","created":"2021-08-21","cited_by_count":26,"area":null},{"id":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26,"area":null},{"id":"2101.05471","title":"Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration","created":"2021-01-14","cited_by_count":25,"area":null},{"id":"2102.07158","title":"Distributed Second Order Methods with Fast Rates and Compressed Communication","created":"2021-02-14","cited_by_count":25,"area":null},{"id":"2109.05109","title":"Toward Communication Efficient Adaptive Gradient Method","created":"2021-09-10","cited_by_count":25,"area":null},{"id":"2204.09715","title":"Scaling Language Model Size in Cross-Device Federated Learning","created":"2022-03-31","cited_by_count":25,"area":null},{"id":"2205.10162","title":"FedAdapter: Efficient Federated Learning for Modern NLP","created":"2022-05-20","cited_by_count":25,"area":null},{"id":"2302.10447","title":"Mask-guided BERT for Few Shot Text Classification","created":"2023-02-21","cited_by_count":25,"area":null},{"id":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"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":"2103.09985","title":"A deep learning theory for neural networks grounded in physics","created":"2021-03-18","cited_by_count":23,"area":null},{"id":"2201.07598","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","created":"2022-01-19","cited_by_count":23,"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":"2405.14578","title":"Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling","created":"2024-05-23","cited_by_count":22,"area":null},{"id":"2406.15244","title":"AdaGrad under Anisotropic Smoothness","created":"2024-06-21","cited_by_count":22,"area":null},{"id":"2506.02285","title":"Why Gradients Rapidly Increase Near the End of Training","created":"2025-06-02","cited_by_count":22,"area":null},{"id":"2102.07245","title":"Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization","created":"2021-02-14","cited_by_count":21,"area":null},{"id":"2110.14807","title":"L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization","created":"2021-10-27","cited_by_count":21,"area":null},{"id":"2204.13169","title":"FedShuffle: Recipes for Better Use of Local Work in Federated Learning","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2210.11350","title":"A Survey on Over-the-Air Computation","created":"2022-10-20","cited_by_count":21,"area":null},{"id":"2305.16150","title":"Unifying GANs and Score-Based Diffusion as Generative Particle Models","created":"2023-05-25","cited_by_count":21,"area":"diffusion"},{"id":"2307.00974","title":"Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions","created":"2023-07-03","cited_by_count":21,"area":null},{"id":"2106.08882","title":"Robust Training in High Dimensions via Block Coordinate Geometric Median Descent","created":"2021-06-16","cited_by_count":20,"area":null},{"id":"2110.02291","title":"FedDQ: Communication-Efficient Federated Learning with Descending Quantization","created":"2021-10-05","cited_by_count":20,"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":"2101.09868","title":"CPT: Efficient Deep Neural Network Training via Cyclic Precision","created":"2021-01-25","cited_by_count":19,"area":null},{"id":"2205.05632","title":"On Distributed Adaptive Optimization with Gradient Compression","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2208.10278","title":"Practical Vertical Federated Learning with Unsupervised Representation Learning","created":"2022-08-13","cited_by_count":19,"area":null},{"id":"2402.07114","title":"Towards Quantifying the Preconditioning Effect of Adam","created":"2024-02-11","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":"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":"2111.15071","title":"Communication-Efficient Federated Learning via Quantized Compressed Sensing","created":"2021-11-30","cited_by_count":18,"area":null},{"id":"2307.10805","title":"Communication-Efficient Split Learning via Adaptive Feature-Wise Compression","created":"2023-07-20","cited_by_count":18,"area":null},{"id":"2311.13171","title":"ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization","created":"2023-11-22","cited_by_count":18,"area":null},{"id":"2404.00438","title":"Communication Efficient Distributed Training with Distributed Lion","created":"2024-03-30","cited_by_count":18,"area":null},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18,"area":null}],"next_cursor":"100"}