{"list":"other","total":74,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"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":"2007.14321","title":"Label-Only Membership Inference Attacks","created":"2020-07-28","cited_by_count":388},{"id":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"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":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"1802.08908","title":"Scalable Private Learning with PATE","created":"2018-02-24","cited_by_count":269},{"id":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224},{"id":"2106.02848","title":"Numerical Composition of Differential Privacy","created":"2021-06-05","cited_by_count":180},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"2205.10487","title":"Scaling Laws and Interpretability of Learning from Repeated Data","created":"2022-05-21","cited_by_count":152},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"1405.7085","title":"Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds","created":"2014-05-27","cited_by_count":107},{"id":"2110.03620","title":"Hyperparameter Tuning with Renyi Differential Privacy","created":"2021-10-07","cited_by_count":104},{"id":"2007.03813","title":"Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification","created":"2020-07-07","cited_by_count":90},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88},{"id":"2201.12328","title":"Toward Training at ImageNet Scale with Differential Privacy","created":"2022-01-28","cited_by_count":87},{"id":"2302.03262","title":"Membership Inference Attacks against Diffusion Models","created":"2023-02-07","cited_by_count":86},{"id":"1811.07971","title":"Private Selection from Private Candidates","created":"2018-11-19","cited_by_count":75},{"id":"2010.09063","title":"Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization","created":"2020-10-18","cited_by_count":58},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54},{"id":"1903.04687","title":"Transfer Adaptation Learning: A Decade Survey","created":"2019-03-12","cited_by_count":52},{"id":"2210.03403","title":"TAN Without a Burn: Scaling Laws of DP-SGD","created":"2022-10-07","cited_by_count":52},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52},{"id":"2112.00193","title":"Public Data-Assisted Mirror Descent for Private Model Training","created":"2021-12-01","cited_by_count":49},{"id":"2205.10683","title":"Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy","created":"2022-05-21","cited_by_count":48},{"id":"2207.00160","title":"When Does Differentially Private Learning Not Suffer in High Dimensions?","created":"2022-07-01","cited_by_count":48},{"id":"2210.00036","title":"Differentially Private Bias-Term Fine-tuning of Foundation Models","created":"2022-09-30","cited_by_count":48},{"id":"2009.03106","title":"Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clipping","created":"2020-09-07","cited_by_count":47},{"id":"2009.05886","title":"Differentially Private Language Models Benefit from Public Pre-training","created":"2020-09-13","cited_by_count":47},{"id":"2210.00597","title":"Composition of Differential Privacy & Privacy Amplification by Subsampling","created":"2022-10-02","cited_by_count":45},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41},{"id":"2202.12219","title":"Debugging Differential Privacy: A Case Study for Privacy Auditing","created":"2022-02-24","cited_by_count":40},{"id":"1910.11519","title":"Limits of Private Learning with Access to Public Data","created":"2019-10-25","cited_by_count":39},{"id":"2102.08598","title":"Leveraging Public Data for Practical Private Query Release","created":"2021-02-17","cited_by_count":39},{"id":"2202.05963","title":"Private Adaptive Optimization with Side Information","created":"2022-02-12","cited_by_count":38},{"id":"2302.09483","title":"Why Is Public Pretraining Necessary for Private Model Training?","created":"2023-02-19","cited_by_count":37},{"id":"2107.07253","title":"MarIA: Spanish Language Models","created":"2021-07-15","cited_by_count":36},{"id":"2207.05739","title":"A Data-Based Perspective on Transfer Learning","created":"2022-07-12","cited_by_count":32},{"id":"2208.07984","title":"Private Estimation with Public Data","created":"2022-08-16","cited_by_count":32},{"id":"2102.03013","title":"Fast and Memory Efficient Differentially Private-SGD via JL Projections","created":"2021-02-05","cited_by_count":29},{"id":"2004.10941","title":"Private Query Release Assisted by Public Data","created":"2020-04-23","cited_by_count":27},{"id":"2111.04906","title":"The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection","created":"2021-11-09","cited_by_count":25},{"id":"2008.00331","title":"Learning from Mixtures of Private and Public Populations","created":"2020-08-01","cited_by_count":19},{"id":"2303.01256","title":"Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance","created":"2023-03-02","cited_by_count":16},{"id":"2207.04381","title":"Faster Privacy Accounting via Evolving Discretization","created":"2022-07-10","cited_by_count":15},{"id":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13},{"id":"2302.09042","title":"Privately Customizing Prefinetuning to Better Match User Data in Federated Learning","created":"2023-02-17","cited_by_count":12},{"id":"2212.04486","title":"A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization","created":"2022-12-08","cited_by_count":11},{"id":"2107.02565","title":"Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)","created":"2021-07-06","cited_by_count":7},{"id":"2011.03186","title":"Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning","created":"2020-11-06","cited_by_count":4},{"id":"2210.08248","title":"A Closer Look at the Calibration of Differentially Private Learners","created":"2022-10-15","cited_by_count":4}],"next_cursor":null}