{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"1908.05355","title":"The generalization error of random features regression: Precise asymptotics and double descent curve","created":"2019-08-14","cited_by_count":413},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"1802.07927","title":"The Hidden Vulnerability of Distributed Learning in Byzantium","created":"2018-02-22","cited_by_count":329},{"id":"1311.0776","title":"The Composition Theorem for Differential Privacy","created":"2013-11-04","cited_by_count":297},{"id":"2011.01403","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","created":"2020-11-03","cited_by_count":276},{"id":"2006.05987","title":"Revisiting Few-sample BERT Fine-tuning","created":"2020-06-10","cited_by_count":238},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"1903.07571","title":"Two models of double descent for weak features","created":"2019-03-18","cited_by_count":195},{"id":"1802.01396","title":"To understand deep learning we need to understand kernel learning","created":"2018-02-05","cited_by_count":187},{"id":"2108.13323","title":"FedKD: Communication Efficient Federated Learning via Knowledge Distillation","created":"2021-08-30","cited_by_count":187},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"2004.12651","title":"Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting","created":"2020-04-27","cited_by_count":170},{"id":"2012.10333","title":"Learning from History for Byzantine Robust Optimization","created":"2020-12-18","cited_by_count":137},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"1604.06968","title":"Agnostic Estimation of Mean and Covariance","created":"2016-04-24","cited_by_count":131},{"id":"2112.02918","title":"When the Curious Abandon Honesty: Federated Learning Is Not Private","created":"2021-12-06","cited_by_count":127},{"id":"2010.02372","title":"Lower Bounds and Optimal Algorithms for Personalized Federated Learning","created":"2020-10-05","cited_by_count":123},{"id":"1903.09139","title":"Harmless interpolation of noisy data in regression","created":"2019-03-21","cited_by_count":121},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2003.01897","title":"Optimal Regularization Can Mitigate Double Descent","created":"2020-03-04","cited_by_count":109},{"id":"1604.02390","title":"Minimax Optimal Procedures for Locally Private Estimation","created":"2016-04-08","cited_by_count":107},{"id":"2011.04946","title":"When Do You Need Billions of Words of Pretraining Data?","created":"2020-11-10","cited_by_count":104},{"id":"2012.06421","title":"When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?","created":"2020-12-11","cited_by_count":104},{"id":"1911.05911","title":"Recent Advances in Algorithmic High-Dimensional Robust Statistics","created":"2019-11-14","cited_by_count":101},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97},{"id":"1806.09471","title":"Does data interpolation contradict statistical optimality?","created":"2018-06-25","cited_by_count":95},{"id":"1311.3158","title":"Fingerprinting Codes and the Price of Approximate Differential Privacy","created":"2013-11-13","cited_by_count":82},{"id":"2009.06807","title":"The Radicalization Risks of GPT-3 and Advanced Neural Language Models","created":"2020-09-15","cited_by_count":76},{"id":"2002.09464","title":"Private Mean Estimation of Heavy-Tailed Distributions","created":"2020-02-21","cited_by_count":73},{"id":"2111.07380","title":"Eluding Secure Aggregation in Federated Learning via Model Inconsistency","created":"2021-11-14","cited_by_count":67},{"id":"2205.12173","title":"Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums","created":"2022-05-24","cited_by_count":63},{"id":"2108.12944","title":"Selective Differential Privacy for Language Modeling","created":"2021-08-30","cited_by_count":62},{"id":"1911.10071","title":"Federated Learning with Bayesian Differential Privacy","created":"2019-11-22","cited_by_count":60},{"id":"2204.06974","title":"Planting Undetectable Backdoors in Machine Learning Models","created":"2022-04-14","cited_by_count":59},{"id":"1501.06095","title":"Between Pure and Approximate Differential Privacy","created":"2015-01-24","cited_by_count":56},{"id":"2002.08404","title":"Implicit Regularization of Random Feature Models","created":"2020-02-19","cited_by_count":54},{"id":"2008.00742","title":"Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)","created":"2020-08-03","cited_by_count":54},{"id":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51},{"id":"2112.06274","title":"SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification","created":"2021-12-12","cited_by_count":46},{"id":"2007.10099","title":"Early Stopping in Deep Networks: Double Descent and How to Eliminate it","created":"2020-07-20","cited_by_count":41},{"id":"2105.02221","title":"How Fine-Tuning Allows for Effective Meta-Learning","created":"2021-05-05","cited_by_count":41},{"id":"1811.09380","title":"High-Dimensional Robust Mean Estimation in Nearly-Linear Time","created":"2018-11-23","cited_by_count":39},{"id":"2010.02681","title":"Kernel regression in high dimensions: Refined analysis beyond double descent","created":"2020-10-06","cited_by_count":39},{"id":"2009.13676","title":"The Grey Hoodie Project: Big Tobacco, Big Tech, and the threat on academic integrity","created":"2020-09-28","cited_by_count":38},{"id":"1906.03058","title":"Robust subgaussian estimation of a mean vector in nearly linear time","created":"2019-06-07","cited_by_count":37},{"id":"1912.03194","title":"Why are Adaptive Methods Good for Attention Models?","created":"2019-12-06","cited_by_count":35},{"id":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","cited_by_count":34},{"id":"2101.09337","title":"Approximate Byzantine Fault-Tolerance in Distributed Optimization","created":"2021-01-22","cited_by_count":28},{"id":"2011.02352","title":"The Limits of Differential Privacy (and its Misuse in Data Release and Machine Learning)","created":"2020-11-04","cited_by_count":22},{"id":"2009.04872","title":"Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning","created":"2020-09-10","cited_by_count":20},{"id":"2005.07866","title":"Byzantine-Resilient SGD in High Dimensions on Heterogeneous Data","created":"2020-05-16","cited_by_count":17},{"id":"2202.08578","title":"An Equivalence Between Data Poisoning and Byzantine Gradient Attacks","created":"2022-02-17","cited_by_count":16},{"id":"2209.10931","title":"Robust Collaborative Learning with Linear Gradient Overhead","created":"2022-09-22","cited_by_count":12},{"id":"2010.01851","title":"On the Universality of the Double Descent Peak in Ridgeless Regression","created":"2020-10-05","cited_by_count":11},{"id":"2107.07334","title":"Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments","created":"2021-05-29","cited_by_count":11},{"id":"2101.05405","title":"Training Data Leakage Analysis in Language Models","created":"2021-01-14","cited_by_count":7},{"id":"2101.06914","title":"Capitol (Pat)riots: A comparative study of Twitter and Parler","created":"2021-01-18","cited_by_count":6},{"id":"2202.08656","title":"Robust Sparse Voting","created":"2022-02-17","cited_by_count":4},{"id":"1612.02914","title":"Lower Bounds for Differential Privacy from Gaussian Width","created":"2016-12-09","cited_by_count":3},{"id":"1901.00752","title":"Building a Sybil-Resilient Digital Community Utilizing Trust-Graph Connectivity","created":"2019-01-03","cited_by_count":3},{"id":"2011.02412","title":"Identity and Personhood in Digital Democracy: Evaluating Inclusion, Equality, Security, and Privacy in Pseudonym Parties and Other Proofs of Personhood","created":"2020-11-04","cited_by_count":3}],"next_cursor":null}