{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2109.12298","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","created":"2021-09-25","cited_by_count":383},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"1311.0776","title":"The Composition Theorem for Differential Privacy","created":"2013-11-04","cited_by_count":297},{"id":"1407.6981","title":"RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response","created":"2014-07-25","cited_by_count":272},{"id":"1807.01647","title":"Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences","created":"2018-07-04","cited_by_count":242},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224},{"id":"1908.10530","title":"R\\'enyi Differential Privacy of the Sampled Gaussian Mechanism","created":"2019-08-28","cited_by_count":204},{"id":"2103.00039","title":"Practical and Private (Deep) Learning without Sampling or Shuffling","created":"2021-02-26","cited_by_count":170},{"id":"1811.12469","title":"Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity","created":"2018-11-29","cited_by_count":164},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153},{"id":"1712.01524","title":"Collecting Telemetry Data Privately","created":"2017-12-05","cited_by_count":149},{"id":"2210.09929","title":"Differentially Private Diffusion Models","created":"2022-10-18","cited_by_count":119},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2006.08265","title":"GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators","created":"2020-06-15","cited_by_count":117},{"id":"1911.11607","title":"Deep Learning with Gaussian Differential Privacy","created":"2019-11-26","cited_by_count":114},{"id":"2210.14348","title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe","created":"2022-10-25","cited_by_count":108},{"id":"2012.12803","title":"Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling","created":"2020-12-23","cited_by_count":96},{"id":"2201.12328","title":"Toward Training at ImageNet Scale with Differential Privacy","created":"2022-01-28","cited_by_count":87},{"id":"2106.08567","title":"Optimal Accounting of Differential Privacy via Characteristic Function","created":"2021-06-16","cited_by_count":86},{"id":"1510.08560","title":"Why Random Reshuffling Beats Stochastic Gradient Descent","created":"2015-10-29","cited_by_count":79},{"id":"1806.10077","title":"Random Shuffling Beats SGD after Finite Epochs","created":"2018-06-26","cited_by_count":67},{"id":"2002.08246","title":"A Unified Convergence Analysis for Shuffling-Type Gradient Methods","created":"2020-02-19","cited_by_count":58},{"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":"2401.04343","title":"Private Fine-tuning of Large Language Models with Zeroth-order Optimization","created":"2024-01-09","cited_by_count":41},{"id":"2208.04591","title":"Stronger Privacy Amplification by Shuffling for R\\'enyi and Approximate Differential Privacy","created":"2022-08-09","cited_by_count":29},{"id":"1709.10432","title":"Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling","created":"2017-09-29","cited_by_count":23},{"id":"2403.17673","title":"How Private are DP-SGD Implementations?","created":"2024-03-26","cited_by_count":22},{"id":"2501.18914","title":"Scaling Laws for Differentially Private Language Models","created":"2025-01-31","cited_by_count":22},{"id":"2210.03458","title":"PAC Privacy: Automatic Privacy Measurement and Control of Data Processing","created":"2022-10-07","cited_by_count":19},{"id":"2411.04205","title":"Scalable DP-SGD: Shuffling vs. Poisson Subsampling","created":"2024-11-06","cited_by_count":16},{"id":"2012.07828","title":"Robustness Threats of Differential Privacy","created":"2020-12-14","cited_by_count":15},{"id":"2502.08202","title":"Privacy amplification by random allocation","created":"2025-02-12","cited_by_count":15},{"id":"2412.16802","title":"Balls-and-Bins Sampling for DP-SGD","created":"2024-12-21","cited_by_count":14},{"id":"2003.04493","title":"Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion","created":"2020-03-10","cited_by_count":13},{"id":"2105.07985","title":"Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning","created":"2021-05-17","cited_by_count":13},{"id":"2310.19973","title":"Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy","created":"2023-10-30","cited_by_count":13},{"id":"2111.13895","title":"Towards Understanding the Impact of Model Size on Differential Private Classification","created":"2021-11-27","cited_by_count":10},{"id":"2408.10456","title":"Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement","created":"2024-08-19","cited_by_count":8},{"id":"2503.03043","title":"Leveraging Randomness in Model and Data Partitioning for Privacy Amplification","created":"2025-03-04","cited_by_count":7},{"id":"2403.07842","title":"DP-TLDM: Differentially Private Tabular Latent Diffusion Model","created":"2024-03-12","cited_by_count":5},{"id":"2502.17772","title":"An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses","created":"2025-02-25","cited_by_count":4}],"next_cursor":null}