{"total":97,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2104.06683","title":"The Curious Case of Hallucinations in Neural Machine Translation","created":"2021-04-14","cited_by_count":161,"area":null},{"id":"2311.06750","title":"Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark","created":"2023-11-12","cited_by_count":99,"area":null},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2109.06141","title":"On Tilted Losses in Machine Learning: Theory and Applications","created":"2021-09-13","cited_by_count":43,"area":null},{"id":"2205.10920","title":"Test-Time Robust Personalization for Federated Learning","created":"2022-05-22","cited_by_count":39,"area":null},{"id":"2202.01136","title":"Probabilistically Robust Learning: Balancing Average- and Worst-case Performance","created":"2022-02-02","cited_by_count":37,"area":null},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2207.08768","title":"Rank-based Decomposable Losses in Machine Learning: A Survey","created":"2022-07-18","cited_by_count":26,"area":null},{"id":"2201.00072","title":"BARACK: Partially Supervised Group Robustness With Guarantees","created":"2021-12-31","cited_by_count":25,"area":null},{"id":"2201.08304","title":"Minimax Demographic Group Fairness in Federated Learning","created":"2022-01-20","cited_by_count":24,"area":null},{"id":"2108.02741","title":"GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning","created":"2021-08-05","cited_by_count":21,"area":null},{"id":"2202.01666","title":"Proportional Fairness in Federated Learning","created":"2022-02-03","cited_by_count":21,"area":null},{"id":"2102.06004","title":"Fairness-Aware PAC Learning from Corrupted Data","created":"2021-02-11","cited_by_count":18,"area":null},{"id":"2202.07530","title":"Optimal Algorithms for Stochastic Multi-Level Compositional Optimization","created":"2022-02-15","cited_by_count":17,"area":null},{"id":"2210.05740","title":"Stochastic Constrained DRO with a Complexity Independent of Sample Size","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2202.00195","title":"Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2401.04993","title":"AdaFed: Fair Federated Learning via Adaptive Common Descent Direction","created":"2024-01-10","cited_by_count":13,"area":null},{"id":"2103.14051","title":"Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation","created":"2021-03-25","cited_by_count":12,"area":null},{"id":"2205.13577","title":"Understanding new tasks through the lens of training data via exponential tilting","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2406.00661","title":"Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift","created":"2024-06-02","cited_by_count":10,"area":null},{"id":"2110.01999","title":"Federating for Learning Group Fair Models","created":"2021-10-05","cited_by_count":9,"area":null},{"id":"2110.11205","title":"Robustness through Data Augmentation Loss Consistency","created":"2021-10-21","cited_by_count":8,"area":null},{"id":"2306.05764","title":"Fair yet Asymptotically Equal Collaborative Learning","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2212.05149","title":"Stochastic Optimization for Spectral Risk Measures","created":"2022-12-10","cited_by_count":7,"area":null},{"id":"2309.17337","title":"Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2412.04346","title":"Distributionally Robust Performative Prediction","created":"2024-12-05","cited_by_count":7,"area":null},{"id":"2206.13648","title":"Supervised Learning with General Risk Functionals","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2306.05325","title":"Federated Learning under Covariate Shifts with Generalization Guarantees","created":"2023-06-08","cited_by_count":6,"area":null},{"id":"2306.09222","title":"Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2307.13381","title":"Scaff-PD: Communication Efficient Fair and Robust Federated Learning","created":"2023-07-25","cited_by_count":6,"area":null},{"id":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2208.13810","title":"DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs","created":"2022-08-29","cited_by_count":5,"area":null},{"id":"2211.05656","title":"On Proper Learnability between Average- and Worst-case Robustness","created":"2022-11-10","cited_by_count":5,"area":null},{"id":"2309.07085","title":"Mitigating Group Bias in Federated Learning for Heterogeneous Devices","created":"2023-09-13","cited_by_count":5,"area":null},{"id":"2501.10877","title":"Distributed Quasi-Newton Method for Fair and Fast Federated Learning","created":"2025-01-18","cited_by_count":5,"area":null},{"id":"2503.00419","title":"Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update","created":"2025-03-01","cited_by_count":5,"area":null},{"id":"2106.06921","title":"Heterogeneous Federated Learning using Dynamic Model Pruning and Adaptive Gradient","created":"2021-06-13","cited_by_count":4,"area":null},{"id":"2110.04996","title":"A Survey of Learning Criteria Going Beyond the Usual Risk","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2206.02786","title":"(Im)possibility of Collective Intelligence","created":"2022-06-05","cited_by_count":4,"area":null},{"id":"2208.13499","title":"Generalization In Multi-Objective Machine Learning","created":"2022-08-29","cited_by_count":4,"area":null},{"id":"2301.12407","title":"Entropy-driven Fair and Effective Federated Learning","created":"2023-01-29","cited_by_count":4,"area":null},{"id":"2302.08872","title":"Revisiting adversarial training for the worst-performing class","created":"2023-02-17","cited_by_count":4,"area":null},{"id":"2310.17584","title":"A minimax optimal control approach for robust neural ODEs","created":"2023-10-26","cited_by_count":4,"area":null},{"id":"2312.03259","title":"f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2405.19272","title":"Differentially Private Clustered Federated Learning","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2409.19431","title":"Generalization and Robustness of the Tilted Empirical Risk","created":"2024-09-28","cited_by_count":4,"area":null},{"id":"2410.21764","title":"Adaptive Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Learning","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2203.14434","title":"Flexible risk design using bi-directional dispersion","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2205.10454","title":"E2FL: Equal and Equitable Federated Learning","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2205.13094","title":"Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2210.06759","title":"Outlier-Robust Group Inference via Gradient Space Clustering","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2310.10006","title":"Soft ascent-descent as a stable and flexible alternative to flooding","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2501.03392","title":"Over-the-Air Fair Federated Learning via Multi-Objective Optimization","created":"2025-01-06","cited_by_count":3,"area":null},{"id":"2208.03066","title":"Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity","created":"2022-08-05","cited_by_count":2,"area":null},{"id":"2310.02698","title":"Enhanced Federated Optimization: Adaptive Unbiased Client Sampling with Reduced Variance","created":"2023-10-04","cited_by_count":2,"area":null},{"id":"2405.20821","title":"Pursuing Overall Welfare in Federated Learning through Sequential Decision Making","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2410.19765","title":"A New Perspective to Boost Performance Fairness for Medical Federated Learning","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2504.15924","title":"Achieving Distributive Justice in Federated Learning via Uncertainty Quantification","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2507.15240","title":"Exact Reformulation and Optimization for Direct Metric Optimization in Binary Imbalanced Classification","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2406.16193","title":"Semi-Variance Reduction for Fair Federated Learning","created":"2024-06-23","cited_by_count":1,"area":null},{"id":"2408.09157","title":"On the KL-Divergence-based Robust Satisficing Model","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2410.20141","title":"FedMABA: Towards Fair Federated Learning through Multi-Armed Bandits Allocation","created":"2024-10-26","cited_by_count":1,"area":null},{"id":"2508.16973","title":"Balanced Sharpness-Aware Minimization for Imbalanced Regression","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2602.02877","title":"A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2106.11732","title":"FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data","created":"2021-06-22","cited_by_count":0,"area":null},{"id":"2112.09429","title":"Federated Learning with Superquantile Aggregation for Heterogeneous Data","created":"2021-12-17","cited_by_count":0,"area":null},{"id":"2205.14676","title":"Diminishing Empirical Risk Minimization for Unsupervised Anomaly Detection","created":"2022-05-29","cited_by_count":0,"area":null},{"id":"2206.10982","title":"Diagnostic Tool for Out-of-Sample Model Evaluation","created":"2022-06-22","cited_by_count":0,"area":null},{"id":"2209.03438","title":"SmOOD: Smoothness-based Out-of-Distribution Detection Approach for Surrogate Neural Networks in Aircraft Design","created":"2022-09-07","cited_by_count":0,"area":null},{"id":"2210.06630","title":"Fairness via Adversarial Attribute Neighbourhood Robust Learning","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2212.05430","title":"Corruption-tolerant Algorithms for Generalized Linear Models","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2301.11584","title":"Robust variance-regularized risk minimization with concomitant scaling","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2301.11724","title":"Meta-Learning Mini-Batch Risk Functionals","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2302.03567","title":"From Utilitarian to Rawlsian Designs for Algorithmic Fairness","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2305.02728","title":"Can Fair Federated Learning reduce the need for Personalisation?","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2308.07424","title":"Addressing Distribution Shift in RTB Markets via Exponential Tilting","created":"2023-08-14","cited_by_count":0,"area":null},{"id":"2311.01047","title":"Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2402.09802","title":"Criterion Collapse and Loss Distribution Control","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2408.03619","title":"Making Robust Generalizers Less Rigid with Loss Concentration","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2409.03703","title":"Iterative thresholding for non-linear learning in the strong $\\varepsilon$-contamination model","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2409.09108","title":"Trimming the Risk: Towards Reliable Continuous Training for Deep Learning Inspection Systems","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2503.13537","title":"FedTilt: Towards Multi-Level Fairness-Preserving and Robust Federated Learning","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2509.15141","title":"Benefits of Online Tilted Empirical Risk Minimization: A Case Study of Outlier Detection and Robust Regression","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.23325","title":"Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2510.15222","title":"Stress-Aware Learning under KL Drift via Trust-Decayed Mirror Descent","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2604.20111","title":"Meta Additive Model: Interpretable Sparse Learning With Auto Weighting","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.15134","title":"Training ML Models with Predictable Failures","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.27747","title":"Soft Specialists: $\\alpha$-R\\'enyi Ensembles for Uncertainty-Aware LLM Post-Training","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.28165","title":"Unification and Optimization of Robust Supervised Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2610.01572","title":"Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.10361","title":"ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated Learning","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13508","title":"FedPCD: Priority-Constrained Federated Aggregation","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.20264","title":"FUSE: Fairness-aware Update Screening against Byzantine Exploitation in $q$-Fair Federated Learning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}