{"list":"other","total":87,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"1911.03030","title":"Certified Data Removal from Machine Learning Models","created":"2019-11-08","cited_by_count":535},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2006.04088","title":"An Efficient Framework for Clustered Federated Learning","created":"2020-06-07","cited_by_count":511},{"id":"1910.01991","title":"Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints","created":"2019-10-04","cited_by_count":503},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"2103.03279","title":"Remember What You Want to Forget: Algorithms for Machine Unlearning","created":"2021-03-04","cited_by_count":371},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2002.10619","title":"Three Approaches for Personalization with Applications to Federated Learning","created":"2020-02-25","cited_by_count":325},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"id":"2006.14651","title":"Influence Functions in Deep Learning Are Fragile","created":"2020-06-25","cited_by_count":252},{"id":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","cited_by_count":159},{"id":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"2211.08413","title":"Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges","created":"2022-11-15","cited_by_count":138},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"2012.15781","title":"FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging","created":"2020-12-31","cited_by_count":120},{"id":"2110.02444","title":"Influence-Balanced Loss for Imbalanced Visual Classification","created":"2021-10-06","cited_by_count":91},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87},{"id":"2209.01188","title":"Petals: Collaborative Inference and Fine-tuning of Large Models","created":"2022-09-02","cited_by_count":87},{"id":"2306.01603","title":"Decentralized Federated Learning: A Survey and Perspective","created":"2023-06-02","cited_by_count":86},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81},{"id":"1909.08525","title":"Measure Contribution of Participants in Federated Learning","created":"2019-09-17","cited_by_count":79},{"id":"1911.00418","title":"On Second-Order Group Influence Functions for Black-Box Predictions","created":"2019-11-01","cited_by_count":79},{"id":"2102.05262","title":"Input Similarity from the Neural Network Perspective","created":"2021-02-10","cited_by_count":79},{"id":"2006.14026","title":"Subpopulation Data Poisoning Attacks","created":"2020-06-24","cited_by_count":70},{"id":"2006.08085","title":"Optimal Complexity in Decentralized Training","created":"2020-06-15","cited_by_count":60},{"id":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59},{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56},{"id":"1702.05122","title":"Exact Diffusion for Distributed Optimization and Learning --- Part I: Algorithm Development","created":"2017-02-16","cited_by_count":50},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46},{"id":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","cited_by_count":46},{"id":"2312.08361","title":"Distributed Inference and Fine-tuning of Large Language Models Over The Internet","created":"2023-12-13","cited_by_count":42},{"id":"2110.04175","title":"RelaySum for Decentralized Deep Learning on Heterogeneous Data","created":"2021-10-08","cited_by_count":39},{"id":"2106.15406","title":"A Comprehensive Survey of Incentive Mechanism for Federated Learning","created":"2021-06-27","cited_by_count":38},{"id":"2202.00787","title":"Achieving Fairness at No Utility Cost via Data Reweighing with Influence","created":"2022-02-01","cited_by_count":38},{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38},{"id":"1910.12308","title":"Asynchronous Decentralized SGD with Quantized and Local Updates","created":"2019-10-27","cited_by_count":36},{"id":"2201.10055","title":"Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation","created":"2022-01-25","cited_by_count":32},{"id":"2204.04452","title":"Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data","created":"2022-04-09","cited_by_count":32},{"id":"2206.10870","title":"Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks","created":"2022-06-22","cited_by_count":32},{"id":"2202.01545","title":"Byzantine-Robust Decentralized Learning via ClippedGossip","created":"2022-02-03","cited_by_count":31},{"id":"2403.05812","title":"Algorithmic progress in language models","created":"2024-03-09","cited_by_count":31},{"id":"2206.03093","title":"Beyond spectral gap: The role of the topology in decentralized learning","created":"2022-06-07","cited_by_count":27},{"id":"2203.12964","title":"Knowledge Removal in Sampling-based Bayesian Inference","created":"2022-03-24","cited_by_count":21},{"id":"2210.12839","title":"Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity","created":"2022-10-23","cited_by_count":21},{"id":"2210.14026","title":"SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication","created":"2022-10-25","cited_by_count":21},{"id":"2412.01152","title":"INTELLECT-1 Technical Report","created":"2024-12-02","cited_by_count":21},{"id":"2405.01031","title":"The Privacy Power of Correlated Noise in Decentralized Learning","created":"2024-05-02","cited_by_count":18},{"id":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15},{"id":"1809.06958","title":"Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent","created":"2018-09-18","cited_by_count":14},{"id":"2206.15025","title":"On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network","created":"2022-06-30","cited_by_count":14},{"id":"2311.00465","title":"Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization","created":"2023-11-01","cited_by_count":11},{"id":"2306.02939","title":"Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm","created":"2023-06-05","cited_by_count":10},{"id":"2402.03448","title":"Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees","created":"2024-02-05","cited_by_count":10},{"id":"2305.11420","title":"Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence","created":"2023-05-19","cited_by_count":9},{"id":"2310.20369","title":"Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm","created":"2023-10-31","cited_by_count":9},{"id":"1803.09169","title":"FROST -- Fast row-stochastic optimization with uncoordinated step-sizes","created":"2018-03-24","cited_by_count":8},{"id":"2402.07471","title":"Differentially Private Decentralized Learning with Random Walks","created":"2024-02-12","cited_by_count":8},{"id":"2402.10001","title":"Privacy Attacks in Decentralized Learning","created":"2024-02-15","cited_by_count":8},{"id":"2205.06689","title":"Heavy-Tail Phenomenon in Decentralized SGD","created":"2022-05-13","cited_by_count":6},{"id":"2212.02387","title":"An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization","created":"2022-12-05","cited_by_count":6},{"id":"2407.08632","title":"Generalization Error Matters in Decentralized Learning Under Byzantine Attacks","created":"2024-07-11","cited_by_count":4},{"id":"2304.05354","title":"iDML: Incentivized Decentralized Machine Learning","created":"2023-04-10","cited_by_count":3},{"id":"2312.04740","title":"Train 'n Trade: Foundations of Parameter Markets","created":"2023-12-07","cited_by_count":3},{"id":"2406.20006","title":"On the Trade-off between Flatness and Optimization in Distributed Learning","created":"2024-06-28","cited_by_count":3},{"id":"2305.17052","title":"A Framework for Incentivized Collaborative Learning","created":"2023-05-26","cited_by_count":2},{"id":"2402.09697","title":"On Three-Layer Data Markets","created":"2024-02-15","cited_by_count":2},{"id":"2210.02129","title":"Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks","created":"2022-10-05","cited_by_count":1},{"id":"2406.19261","title":"Commodification of Compute","created":"2024-06-27","cited_by_count":1}],"next_cursor":null}