{"total":74,"rows":[{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442,"area":null},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138,"area":null},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115,"area":null},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"area":null},{"id":"2104.02857","title":"Soft-Label Anonymous Gastric X-ray Image Distillation","created":"2021-04-07","cited_by_count":51,"area":null},{"id":"2210.01738","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","created":"2022-10-04","cited_by_count":47,"area":null},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44,"area":null},{"id":"2103.16774","title":"Towards understanding the power of quantum kernels in the NISQ era","created":"2021-03-31","cited_by_count":43,"area":null},{"id":"2311.01570","title":"Sequential Subset Matching for Dataset Distillation","created":"2023-11-02","cited_by_count":40,"area":null},{"id":"2209.14635","title":"Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing","created":"2022-09-29","cited_by_count":35,"area":null},{"id":"2106.04254","title":"Coresets for Classification -- Simplified and Strengthened","created":"2021-06-08","cited_by_count":28,"area":null},{"id":"2505.17799","title":"A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances","created":"2025-05-23","cited_by_count":28,"area":null},{"id":"2209.14609","title":"Dataset Distillation Using Parameter Pruning","created":"2022-09-29","cited_by_count":27,"area":null},{"id":"2207.02121","title":"Adapting to Online Label Shift with Provable Guarantees","created":"2022-07-05","cited_by_count":26,"area":null},{"id":"2407.14245","title":"Dataset Distillation by Automatic Training Trajectories","created":"2024-07-19","cited_by_count":26,"area":null},{"id":"2209.14603","title":"Dataset Distillation for Medical Dataset Sharing","created":"2022-09-29","cited_by_count":25,"area":null},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2307.02460","title":"Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources","created":"2023-07-05","cited_by_count":16,"area":null},{"id":"2404.05779","title":"Data Readiness for AI: A 360-Degree Survey","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2112.12194","title":"Surrogate Likelihoods for Variational Annealed Importance Sampling","created":"2021-12-22","cited_by_count":14,"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":"2206.00395","title":"Optimization with Access to Auxiliary Information","created":"2022-06-01","cited_by_count":13,"area":null},{"id":"2408.06927","title":"Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator","created":"2024-08-13","cited_by_count":13,"area":null},{"id":"2302.11962","title":"Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods","created":"2023-02-23","cited_by_count":12,"area":null},{"id":"2110.03195","title":"Coresets for Decision Trees of Signals","created":"2021-10-07","cited_by_count":10,"area":null},{"id":"2305.03355","title":"A Comprehensive Study on Dataset Distillation: Performance, Privacy, Robustness and Fairness","created":"2023-05-05","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":"2302.11510","title":"Selective experience replay compression using coresets for lifelong deep reinforcement learning in medical imaging","created":"2023-02-22","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":"2111.06353","title":"Learning from Mistakes -- A Framework for Neural Architecture Search","created":"2021-11-11","cited_by_count":6,"area":null},{"id":"2406.02131","title":"CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2206.07852","title":"Performance analysis of coreset selection for quantum implementation of K-Means clustering algorithm","created":"2022-06-16","cited_by_count":5,"area":null},{"id":"2311.00109","title":"FairWASP: Fast and Optimal Fair Wasserstein Pre-processing","created":"2023-10-31","cited_by_count":5,"area":null},{"id":"2406.15042","title":"Behaviour Distillation","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2102.07834","title":"One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes","created":"2021-02-15","cited_by_count":4,"area":null},{"id":"2106.00886","title":"Partial Wasserstein Covering","created":"2021-06-02","cited_by_count":4,"area":null},{"id":"2211.02377","title":"Black-box Coreset Variational Inference","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2303.14753","title":"Does \"Deep Learning on a Data Diet\" reproduce? Overall yes, but GraNd at Initialization does not","created":"2023-03-26","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":"2309.15696","title":"A Unified View of Differentially Private Deep Generative Modeling","created":"2023-09-27","cited_by_count":4,"area":null},{"id":"2402.05280","title":"No Dimensional Sampling Coresets for Classification","created":"2024-02-07","cited_by_count":4,"area":null},{"id":"2411.00611","title":"Small coresets via negative dependence: DPPs, linear statistics, and concentration","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2502.16703","title":"Subsampling Graphs with GNN Performance Guarantees","created":"2025-02-23","cited_by_count":4,"area":null},{"id":"2306.01869","title":"Fast $(1+\\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2312.00486","title":"REDUCR: Robust Data Downsampling Using Class Priority Reweighting","created":"2023-12-01","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":"2104.10770","title":"Skeleton Clustering: Dimension-Free Density-based Clustering","created":"2021-04-21","cited_by_count":2,"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":"2312.03516","title":"Clustering by Contour coreset and variational quantum eigensolver","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2410.19631","title":"Efficient Biological Data Acquisition through Inference Set Design","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2505.20754","title":"Stationary MMD Points","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2605.30337","title":"Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.02721","title":"Provable Pruning for Efficient 3D Gaussian Splatting via Coresets","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2201.13217","title":"Fast Distributed k-Means with a Small Number of Rounds","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2310.14768","title":"Policy Gradient with Kernel Quadrature","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2312.09885","title":"Simple Weak Coresets for Non-Decomposable Classification Measures","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2410.05800","title":"Core Tokensets for Data-efficient Sequential Training of Transformers","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2504.15144","title":"C2RUST-BENCH: A Minimized, Representative Dataset for C-to-Rust Transpilation Evaluation","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2603.13790","title":"Aligning the Query Space: Greedy Information Projection for Language Model Data Selection","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2605.13127","title":"State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2303.05102","title":"StyleDiff: Attribute Comparison Between Unlabeled Datasets in Latent Disentangled Space","created":"2023-03-09","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":"2508.12758","title":"Constrained Centroid Clustering: A Novel Approach for Compact and Structured Partitioning","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2509.21380","title":"Coreset selection based on Intra-class diversity","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2509.21748","title":"SubZeroCore: A Submodular Approach with Zero Training for Coreset Selection","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2601.02081","title":"ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.20694","title":"Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.14900","title":"COREKG: Coreset-Guided Personalized Summarization of Knowledge Graphs","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.29448","title":"How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.05265","title":"Data-efficient flood depth prediction through domain-aware coreset selection and tabular foundation models","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2609.06394","title":"Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.08172","title":"Optimal Slice-Adaptive Tuning of Hybrid Slice Sampling","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}