{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1803.00567","title":"Computational Optimal Transport","created":"2018-03-01","cited_by_count":780},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1804.00792","title":"Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks","created":"2018-04-03","cited_by_count":519},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"1706.00292","title":"Learning Generative Models with Sinkhorn Divergences","created":"2017-06-01","cited_by_count":314},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230},{"id":"1310.4375","title":"Fast Computation of Wasserstein Barycenters","created":"2013-10-16","cited_by_count":216},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"1605.08527","title":"Stochastic Optimization for Large-scale Optimal Transport","created":"2016-05-27","cited_by_count":189},{"id":"2110.14049","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","created":"2021-10-26","cited_by_count":165},{"id":"2002.02923","title":"Geometric Dataset Distances via Optimal Transport","created":"2020-02-07","cited_by_count":158},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"1908.08619","title":"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms","created":"2019-08-22","cited_by_count":148},{"id":"2205.15466","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","created":"2022-05-30","cited_by_count":132},{"id":"1511.06343","title":"Online Batch Selection for Faster Training of Neural Networks","created":"2015-11-19","cited_by_count":122},{"id":"1802.04367","title":"Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm","created":"2018-02-12","cited_by_count":112},{"id":"1910.00762","title":"Accelerating Deep Learning by Focusing on the Biggest Losers","created":"2019-10-02","cited_by_count":94},{"id":"2305.00054","title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms","created":"2023-04-28","cited_by_count":69},{"id":"2103.04737","title":"Low-Rank Sinkhorn Factorization","created":"2021-03-08","cited_by_count":67},{"id":"2306.10577","title":"OpenDataVal: a Unified Benchmark for Data Valuation","created":"2023-06-18","cited_by_count":55},{"id":"1902.00342","title":"Tree-Sliced Variants of Wasserstein Distances","created":"2019-02-01","cited_by_count":54},{"id":"1906.10827","title":"Hierarchical Optimal Transport for Document Representation","created":"2019-06-26","cited_by_count":53},{"id":"1812.05189","title":"Massively scalable Sinkhorn distances via the Nystr\\\"om method","created":"2018-12-12","cited_by_count":41},{"id":"1806.07348","title":"Statistical Optimal Transport via Factored Couplings","created":"2018-06-19","cited_by_count":38},{"id":"1906.11768","title":"Hierarchical Optimal Transport for Multimodal Distribution Alignment","created":"2019-06-27","cited_by_count":38},{"id":"2304.07718","title":"Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value","created":"2023-04-16","cited_by_count":38},{"id":"2010.14499","title":"A Bayesian Perspective on Training Speed and Model Selection","created":"2020-10-27","cited_by_count":19},{"id":"2308.15709","title":"Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation","created":"2023-08-30","cited_by_count":19},{"id":"2202.10723","title":"Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics","created":"2022-02-22","cited_by_count":18},{"id":"2401.11103","title":"Efficient Data Shapley for Weighted Nearest Neighbor Algorithms","created":"2024-01-20","cited_by_count":18},{"id":"2401.15889","title":"Sliced Wasserstein with Random-Path Projecting Directions","created":"2024-01-29","cited_by_count":15},{"id":"2302.12498","title":"Scalable Unbalanced Sobolev Transport for Measures on a Graph","created":"2023-02-24","cited_by_count":10},{"id":"2402.04516","title":"Generalized Sobolev Transport for Probability Measures on a Graph","created":"2024-02-07","cited_by_count":9},{"id":"2310.13653","title":"Optimal Transport for Measures with Noisy Tree Metric","created":"2023-10-20","cited_by_count":7}],"next_cursor":null}