{"total":44,"rows":[{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127,"area":null},{"id":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124,"area":null},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38,"area":null},{"id":"2312.16627","title":"MIM4DD: Mutual Information Maximization for Dataset Distillation","created":"2023-12-27","cited_by_count":21,"area":null},{"id":"2111.03044","title":"A Unified Approach to Coreset Learning","created":"2021-11-04","cited_by_count":18,"area":null},{"id":"2106.14952","title":"Adversarial Robustness of Streaming Algorithms through Importance Sampling","created":"2021-06-28","cited_by_count":13,"area":null},{"id":"2110.08991","title":"Dimensionality Reduction for Wasserstein Barycenter","created":"2021-10-18","cited_by_count":13,"area":null},{"id":"2502.12976","title":"Does Training with Synthetic Data Truly Protect Privacy?","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2112.00378","title":"$\\ell_\\infty$-Robustness and Beyond: Unleashing Efficient Adversarial Training","created":"2021-12-01","cited_by_count":11,"area":null},{"id":"2209.05785","title":"Adversarial Coreset Selection for Efficient Robust Training","created":"2022-09-13","cited_by_count":9,"area":null},{"id":"2507.20208","title":"From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation","created":"2025-07-27","cited_by_count":9,"area":null},{"id":"2109.12534","title":"Data Summarization via Bilevel Optimization","created":"2021-09-26","cited_by_count":8,"area":null},{"id":"2110.15263","title":"Coresets for Time Series Clustering","created":"2021-10-28","cited_by_count":8,"area":null},{"id":"2304.10036","title":"Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations","created":"2023-04-20","cited_by_count":7,"area":null},{"id":"2307.08086","title":"Dataset Distillation Meets Provable Subset Selection","created":"2023-07-16","cited_by_count":7,"area":null},{"id":"2403.07329","title":"Unknown Domain Inconsistency Minimization for Domain Generalization","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2107.00068","title":"Robust and Fully-Dynamic Coreset for Continuous-and-Bounded Learning (With Outliers) Problems","created":"2021-06-30","cited_by_count":6,"area":null},{"id":"2303.02095","title":"Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective","created":"2023-03-03","cited_by_count":6,"area":null},{"id":"2304.11251","title":"Machine Learning and the Future of Bayesian Computation","created":"2023-04-21","cited_by_count":4,"area":null},{"id":"2309.10441","title":"Coreset selection can accelerate quantum machine learning models with provable generalization","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2404.01936","title":"Settling Time vs. Accuracy Tradeoffs for Clustering Big Data","created":"2024-04-02","cited_by_count":4,"area":null},{"id":"2412.04748","title":"Decomposed Distribution Matching in Dataset Condensation","created":"2024-12-06","cited_by_count":3,"area":null},{"id":"2504.14572","title":"Data Selection for ERMs","created":"2025-04-20","cited_by_count":3,"area":null},{"id":"2310.16752","title":"Simple, Scalable and Effective Clustering via One-Dimensional Projections","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2405.11780","title":"General bounds on the quality of Bayesian coresets","created":"2024-05-20","cited_by_count":2,"area":null},{"id":"2204.12073","title":"One-pass additive-error subset selection for $\\ell_{p}$ subspace approximation","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2407.07450","title":"Using Low-Discrepancy Points for Data Compression in Machine Learning: An Experimental Comparison","created":"2024-07-10","cited_by_count":1,"area":null},{"id":"2506.06033","title":"Large Language Models are Demonstration Pre-Selectors for Themselves","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2510.26185","title":"Accumulative SGD Influence Estimation for Data Attribution","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2604.11810","title":"GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2203.01531","title":"CAFE: Learning to Condense Dataset by Aligning Features","created":"2022-03-03","cited_by_count":0,"area":null},{"id":"2308.05878","title":"Composable Core-sets for Diversity Approximation on Multi-Dataset Streams","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2404.10997","title":"Online Algorithms with Limited Data Retention","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2409.12076","title":"Unsupervised Domain Adaptation Via Data Pruning","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2410.17945","title":"Theoretically Grounded Pruning of Large Ground Sets for Constrained, Discrete Optimization","created":"2024-10-23","cited_by_count":0,"area":null},{"id":"2503.10698","title":"Ordered Semantically Diverse Sampling for Textual Data","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2603.06761","title":"Diversity-Aware Adaptive Collocation for Physics-Informed Neural Networks via Sparse QUBO Optimization and Hybrid Coresets","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2605.14785","title":"Understanding Imbalanced Forgetting in Rehearsal-Based Class-Incremental Learning","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.26628","title":"Understanding Context Sampling in TabPFN on Small Tabular Datasets","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.09047","title":"Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.23260","title":"Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.26962","title":"CRISP: Scalable Importance-Stratified Coresets for Imbalanced Tabular Learning","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}