{"total":92,"rows":[{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533,"area":null},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133,"area":null},{"id":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124,"area":null},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117,"area":null},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93,"area":null},{"id":"2208.00311","title":"Delving into Effective Gradient Matching for Dataset Condensation","created":"2022-07-30","cited_by_count":40,"area":null},{"id":"2106.04254","title":"Coresets for Classification -- Simplified and Strengthened","created":"2021-06-08","cited_by_count":28,"area":null},{"id":"2202.12793","title":"Towards Optimal Lower Bounds for k-median and k-means Coresets","created":"2022-02-25","cited_by_count":23,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"id":"2310.14019","title":"You Only Condense Once: Two Rules for Pruning Condensed Datasets","created":"2023-10-21","cited_by_count":20,"area":null},{"id":"2107.06615","title":"Oblivious sketching for logistic regression","created":"2021-07-14","cited_by_count":18,"area":null},{"id":"2111.03044","title":"A Unified Approach to Coreset Learning","created":"2021-11-04","cited_by_count":18,"area":null},{"id":"2207.08041","title":"Personalized PCA: Decoupling Shared and Unique Features","created":"2022-07-17","cited_by_count":17,"area":null},{"id":"2203.04370","title":"New Coresets for Projective Clustering and Applications","created":"2022-03-08","cited_by_count":16,"area":null},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2207.08268","title":"Online Lewis Weight Sampling","created":"2022-07-17","cited_by_count":15,"area":null},{"id":"2309.07698","title":"Dataset Condensation via Generative Model","created":"2023-09-14","cited_by_count":15,"area":null},{"id":"2506.01701","title":"Data Pruning by Information Maximization","created":"2025-06-02","cited_by_count":15,"area":null},{"id":"2210.14664","title":"Coresets for Vertical Federated Learning: Regularized Linear Regression and $K$-Means Clustering","created":"2022-10-26","cited_by_count":14,"area":null},{"id":"2303.05151","title":"Provable Data Subset Selection For Efficient Neural Network Training","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2102.04152","title":"EigenGame Unloaded: When playing games is better than optimizing","created":"2021-02-08","cited_by_count":13,"area":null},{"id":"2203.05723","title":"Bayesian inference via sparse Hamiltonian flows","created":"2022-03-11","cited_by_count":12,"area":null},{"id":"2203.13568","title":"$p$-Generalized Probit Regression and Scalable Maximum Likelihood Estimation via Sketching and Coresets","created":"2022-03-25","cited_by_count":11,"area":null},{"id":"2310.08782","title":"Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning","created":"2023-10-13","cited_by_count":11,"area":null},{"id":"2110.03195","title":"Coresets for Decision Trees of Signals","created":"2021-10-07","cited_by_count":10,"area":null},{"id":"2110.15263","title":"Coresets for Time Series Clustering","created":"2021-10-28","cited_by_count":8,"area":null},{"id":"2311.15547","title":"Dataset Distillation in Latent Space","created":"2023-11-27","cited_by_count":8,"area":null},{"id":"2402.06730","title":"A Scalable Algorithm for Individually Fair K-means Clustering","created":"2024-02-09","cited_by_count":8,"area":null},{"id":"2207.00966","title":"An Empirical Evaluation of $k$-Means Coresets","created":"2022-07-03","cited_by_count":7,"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":"2203.03009","title":"Coresets for Data Discretization and Sine Wave Fitting","created":"2022-03-06","cited_by_count":6,"area":null},{"id":"2207.00510","title":"Enhancing cluster analysis via topological manifold learning","created":"2022-07-01","cited_by_count":6,"area":null},{"id":"2403.00680","title":"Scalable Learning of Item Response Theory Models","created":"2024-03-01","cited_by_count":6,"area":null},{"id":"2111.03046","title":"Introduction to Coresets: Approximated Mean","created":"2021-11-04","cited_by_count":5,"area":null},{"id":"2211.02377","title":"Black-box Coreset Variational Inference","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2211.15118","title":"A Faster $k$-means++ Algorithm","created":"2022-11-28","cited_by_count":4,"area":null},{"id":"2302.11634","title":"Provably Efficient Reinforcement Learning via Surprise Bound","created":"2023-02-22","cited_by_count":4,"area":null},{"id":"2303.04183","title":"Robustness-preserving Lifelong Learning via Dataset Condensation","created":"2023-03-07","cited_by_count":4,"area":null},{"id":"2303.11278","title":"Bayesian Pseudo-Coresets via Contrastive Divergence","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2310.09127","title":"On Generalization Bounds for Projective Clustering","created":"2023-10-13","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":"2501.06588","title":"A Tight VC-Dimension Analysis of Clustering Coresets with Applications","created":"2025-01-11","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":"2312.05599","title":"Not All Data Matters: An End-to-End Adaptive Dataset Pruning Framework for Enhancing Model Performance and Efficiency","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2406.00328","title":"Optimal bounds for $\\ell_p$ sensitivity sampling via $\\ell_2$ augmentation","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2406.00339","title":"Turnstile $\\ell_p$ leverage score sampling with applications","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2409.14538","title":"Towards Model-Agnostic Dataset Condensation by Heterogeneous Models","created":"2024-09-22","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":"2402.14332","title":"Accelerating data-driven algorithm selection for combinatorial partitioning problems","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2407.03262","title":"Ridge Leverage Score Sampling for $\\ell_p$ Subspace Approximation","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2502.16733","title":"Coreset Selection via LLM-based Concept Bottlenecks","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2504.20982","title":"Provably faster randomized and quantum algorithms for $k$-means clustering via uniform sampling","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2604.20078","title":"Improved large-scale graph learning through ridge spectral sparsification","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2606.00571","title":"On the Difficulty of Learning a Meta-network for Training Data Selection","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2105.11634","title":"Robust Principal Component Analysis Using a Novel Kernel Related with the L1-Norm","created":"2021-05-25","cited_by_count":1,"area":null},{"id":"2106.07203","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","created":"2021-06-14","cited_by_count":1,"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":"2303.08242","title":"Optimal Sampling Designs for Multi-dimensional Streaming Time Series with Application to Power Grid Sensor Data","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2303.17885","title":"Accelerating Wireless Federated Learning via Nesterov's Momentum and Distributed Principle Component Analysis","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2307.07449","title":"Differentially Private Clustering in Data Streams","created":"2023-07-14","cited_by_count":1,"area":null},{"id":"2410.05902","title":"Mini-Batch Kernel $k$-means","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2410.22872","title":"Data subsampling for Poisson regression with pth-root-link","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2412.03332","title":"On Approximability of $\\ell_2^2$ Min-Sum Clustering","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2412.20189","title":"Accurate Coresets for Latent Variable Models and Regularized Regression","created":"2024-12-28","cited_by_count":1,"area":null},{"id":"2502.17615","title":"Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2512.07988","title":"HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2603.19061","title":"Hardness of High-Dimensional Linear Classification","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2102.04282","title":"Communication-efficient k-Means for Edge-based Machine Learning","created":"2021-02-08","cited_by_count":0,"area":null},{"id":"2109.03709","title":"Speeding up PCA with priming","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2110.08045","title":"Compressive Independent Component Analysis: Theory and Algorithms","created":"2021-10-15","cited_by_count":0,"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":"2204.06652","title":"Joint Coreset Construction and Quantization for Distributed Machine Learning","created":"2022-04-13","cited_by_count":0,"area":null},{"id":"2305.16890","title":"Universal Weak Coreset","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2306.00732","title":"Sharper Bounds for $\\ell_p$ Sensitivity Sampling","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2306.06611","title":"Learning the Positions in CountSketch","created":"2023-06-11","cited_by_count":0,"area":null},{"id":"2307.03927","title":"Fast Empirical Scenarios","created":"2023-07-08","cited_by_count":0,"area":null},{"id":"2408.14225","title":"Provable Imbalanced Point Clustering","created":"2024-08-26","cited_by_count":0,"area":null},{"id":"2409.13453","title":"Data Compression using Rank-1 Lattices for Parameter Estimation in Machine Learning","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2506.00165","title":"Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.09594","title":"Accelerating Large-Scale Regularized High-Order Tensor Recovery","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.10775","title":"Monotone Classification with Relative Approximations","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2507.14631","title":"$k$-PCA for (non-squared) Euclidean Distances: Polynomial Time Approximation","created":"2025-07-19","cited_by_count":0,"area":null},{"id":"2509.20484","title":"Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.23438","title":"Coresets for Clustering Under Stochastic Noise","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2601.00361","title":"Deterministic Coreset for Lp Subspace","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2602.00437","title":"Exact Instance Compression for Convex Empirical Risk Minimization via Color Refinement","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2603.19792","title":"Scalable Learning of Multivariate Distributions via Coresets","created":"2026-03-20","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":"2606.18209","title":"Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.03112","title":"Dimension Reduction for Curves: Simplified and Generalized","created":"2026-07-03","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}],"next_cursor":null}