{"total":238,"rows":[{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2403.05527","title":"GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM","created":"2024-03-08","cited_by_count":158,"area":"inference"},{"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":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88,"area":null},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86,"area":null},{"id":"2206.08307","title":"Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning","created":"2022-06-16","cited_by_count":79,"area":null},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75,"area":null},{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68,"area":null},{"id":"2102.01854","title":"Provably Secure Federated Learning against Malicious Clients","created":"2021-02-03","cited_by_count":63,"area":null},{"id":"2102.04487","title":"Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning","created":"2021-02-08","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":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59,"area":null},{"id":"2105.08339","title":"DRIVE: One-bit Distributed Mean Estimation","created":"2021-05-18","cited_by_count":52,"area":null},{"id":"2106.02969","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","created":"2021-06-05","cited_by_count":52,"area":null},{"id":"2202.01889","title":"Generalizing to New Physical Systems via Context-Informed Dynamics Model","created":"2022-02-01","cited_by_count":50,"area":null},{"id":"2108.00951","title":"Rethinking gradient sparsification as total error minimization","created":"2021-08-02","cited_by_count":41,"area":null},{"id":"2206.07284","title":"A Survey on Gradient Inversion: Attacks, Defenses and Future Directions","created":"2022-06-15","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":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35,"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":"2101.10761","title":"An Efficient Statistical-based Gradient Compression Technique for Distributed Training Systems","created":"2021-01-26","cited_by_count":32,"area":null},{"id":"2110.03300","title":"Permutation Compressors for Provably Faster Distributed Nonconvex Optimization","created":"2021-10-07","cited_by_count":32,"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":"2305.15155","title":"Momentum Provably Improves Error Feedback!","created":"2023-05-24","cited_by_count":31,"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":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2503.09799","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","created":"2025-03-12","cited_by_count":27,"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":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24,"area":null},{"id":"2104.11125","title":"ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training","created":"2021-04-21","cited_by_count":22,"area":null},{"id":"2305.18469","title":"Reducing Communication for Split Learning by Randomized Top-k Sparsification","created":"2023-05-29","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":"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":"2110.08133","title":"Trade-offs of Local SGD at Scale: An Empirical Study","created":"2021-10-15","cited_by_count":20,"area":null},{"id":"2201.12023","title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning","created":"2022-01-28","cited_by_count":20,"area":null},{"id":"2207.03957","title":"Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox","created":"2022-07-08","cited_by_count":19,"area":null},{"id":"2210.16402","title":"GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity","created":"2022-10-28","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},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2302.02589","title":"$z$-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning","created":"2023-02-06","cited_by_count":17,"area":null},{"id":"2506.01913","title":"Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2202.00280","title":"Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?","created":"2022-02-01","cited_by_count":16,"area":null},{"id":"2110.03313","title":"Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2201.11865","title":"FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients","created":"2022-01-28","cited_by_count":15,"area":null},{"id":"2301.09830","title":"Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression","created":"2023-01-24","cited_by_count":15,"area":null},{"id":"2311.05645","title":"EControl: Fast Distributed Optimization with Compression and Error Control","created":"2023-11-06","cited_by_count":15,"area":null},{"id":"2403.06664","title":"Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System","created":"2024-03-11","cited_by_count":15,"area":null},{"id":"2201.02664","title":"Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory","created":"2022-01-07","cited_by_count":14,"area":null},{"id":"2203.04925","title":"Correlated quantization for distributed mean estimation and optimization","created":"2022-03-09","cited_by_count":14,"area":null},{"id":"2212.08272","title":"Communication-Efficient Federated Learning for Heterogeneous Edge Devices Based on Adaptive Gradient Quantization","created":"2022-12-16","cited_by_count":14,"area":null},{"id":"2302.03662","title":"Federated Learning with Regularized Client Participation","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2401.03748","title":"Towards Efficient Communication and Secure Federated Recommendation System via Low-rank Training","created":"2024-01-08","cited_by_count":14,"area":null},{"id":"2410.15526","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","created":"2024-10-20","cited_by_count":14,"area":null},{"id":"2106.02797","title":"Neural Distributed Source Coding","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"area":null},{"id":"2405.15861","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2205.03914","title":"Federated Random Reshuffling with Compression and Variance Reduction","created":"2022-05-08","cited_by_count":12,"area":null},{"id":"2301.02654","title":"Does compressing activations help model parallel training?","created":"2023-01-06","cited_by_count":12,"area":null},{"id":"2305.18425","title":"Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals","created":"2023-05-28","cited_by_count":12,"area":null},{"id":"2310.09804","title":"Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates","created":"2023-10-15","cited_by_count":12,"area":null},{"id":"2506.01260","title":"Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2112.02668","title":"On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons","created":"2021-12-05","cited_by_count":11,"area":null},{"id":"2203.15488","title":"Over-the-Air Federated Learning via Second-Order Optimization","created":"2022-03-29","cited_by_count":11,"area":null},{"id":"2305.17581","title":"Knowledge Distillation Performs Partial Variance Reduction","created":"2023-05-27","cited_by_count":11,"area":"distill"},{"id":"2306.00127","title":"Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2411.10619","title":"Electrical Load Forecasting in Smart Grid: A Personalized Federated Learning Approach","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2411.19870","title":"DeMo: Decoupled Momentum Optimization","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2507.08784","title":"Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees","created":"2025-07-11","cited_by_count":11,"area":null},{"id":"2102.06025","title":"Large-Scale Training System for 100-Million Classification at Alibaba","created":"2021-02-09","cited_by_count":10,"area":null},{"id":"2104.12416","title":"Communication-Efficient Federated Learning with Dual-Side Low-Rank Compression","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2108.11976","title":"JUWELS Booster -- A Supercomputer for Large-Scale AI Research","created":"2021-06-30","cited_by_count":10,"area":null},{"id":"2305.12201","title":"GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training","created":"2023-05-20","cited_by_count":10,"area":null},{"id":"2306.11250","title":"InRank: Incremental Low-Rank Learning","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2102.08374","title":"IntSGD: Adaptive Floatless Compression of Stochastic Gradients","created":"2021-02-16","cited_by_count":9,"area":null},{"id":"2106.03524","title":"Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques","created":"2021-06-07","cited_by_count":9,"area":null},{"id":"2110.03294","title":"EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2112.00845","title":"Improving Differentially Private SGD via Randomly Sparsified Gradients","created":"2021-12-01","cited_by_count":8,"area":null},{"id":"2211.06418","title":"Re-Analyze Gauss: Bounds for Private Matrix Approximation via Dyson Brownian Motion","created":"2022-11-11","cited_by_count":8,"area":null},{"id":"2301.08897","title":"ScaDLES: Scalable Deep Learning over Streaming data at the Edge","created":"2023-01-21","cited_by_count":8,"area":null},{"id":"2303.14604","title":"Green Federated Learning","created":"2023-03-26","cited_by_count":8,"area":null},{"id":"2509.26337","title":"FedMuon: Federated Learning with Bias-corrected LMO-based Optimization","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2306.08881","title":"Evaluation and Optimization of Gradient Compression for Distributed Deep Learning","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2307.07950","title":"Accelerating Distributed ML Training via Selective Synchronization","created":"2023-07-16","cited_by_count":7,"area":null},{"id":"2401.07788","title":"Activations and Gradients Compression for Model-Parallel Training","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2402.01342","title":"Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2406.17887","title":"Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2602.03839","title":"Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2202.00255","title":"DoCoM: Compressed Decentralized Optimization with Near-Optimal Sample Complexity","created":"2022-02-01","cited_by_count":6,"area":null},{"id":"2209.05148","title":"Personalized Federated Learning with Communication Compression","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2306.06098","title":"Error Feedback Can Accurately Compress Preconditioners","created":"2023-06-09","cited_by_count":6,"area":null},{"id":"2306.12625","title":"Adaptive Compression in Federated Learning via Side Information","created":"2023-06-22","cited_by_count":6,"area":null},{"id":"2310.13033","title":"LASER: Linear Compression in Wireless Distributed Optimization","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2407.01378","title":"Beyond Throughput and Compression Ratios: Towards High End-to-end Utility of Gradient Compression","created":"2024-07-01","cited_by_count":6,"area":null}],"next_cursor":"100"}