{"list":"other","total":135,"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"1706.02515","title":"Self-Normalizing Neural Networks","created":"2017-06-08","cited_by_count":598},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"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":"2109.12298","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","created":"2021-09-25","cited_by_count":383},{"id":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"id":"1605.02065","title":"Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds","created":"2016-05-06","cited_by_count":346},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"1311.0776","title":"The Composition Theorem for Differential Privacy","created":"2013-11-04","cited_by_count":297},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"1908.11229","title":"White-box vs Black-box: Bayes Optimal Strategies for Membership Inference","created":"2019-08-29","cited_by_count":271},{"id":"1807.01647","title":"Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences","created":"2018-07-04","cited_by_count":242},{"id":"1808.00087","title":"Subsampled R\\'enyi Differential Privacy and Analytical Moments Accountant","created":"2018-07-31","cited_by_count":236},{"id":"1802.06739","title":"Differentially Private Generative Adversarial Network","created":"2018-02-19","cited_by_count":235},{"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":"1905.03871","title":"Differentially Private Learning with Adaptive Clipping","created":"2019-05-09","cited_by_count":220},{"id":"1805.06530","title":"Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising","created":"2018-05-16","cited_by_count":218},{"id":"2006.07709","title":"Auditing Differentially Private Machine Learning: How Private is Private SGD?","created":"2020-06-13","cited_by_count":218},{"id":"1908.10530","title":"R\\'enyi Differential Privacy of the Sampled Gaussian Mechanism","created":"2019-08-28","cited_by_count":204},{"id":"2101.04535","title":"Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning","created":"2021-01-11","cited_by_count":199},{"id":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"1908.09970","title":"Private Stochastic Convex Optimization with Optimal Rates","created":"2019-08-27","cited_by_count":186},{"id":"2006.06914","title":"Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses","created":"2020-06-12","cited_by_count":173},{"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":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148},{"id":"2006.15429","title":"Understanding Gradient Clipping in Private SGD: A Geometric Perspective","created":"2020-06-27","cited_by_count":142},{"id":"1812.00984","title":"Protection Against Reconstruction and Its Applications in Private Federated Learning","created":"2018-12-03","cited_by_count":130},{"id":"2102.06387","title":"The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation","created":"2021-02-12","cited_by_count":128},{"id":"2007.14191","title":"Tempered Sigmoid Activations for Deep Learning with Differential Privacy","created":"2020-07-28","cited_by_count":122},{"id":"1910.08902","title":"Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations","created":"2019-10-20","cited_by_count":119},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2102.06062","title":"Deep Learning with Label Differential Privacy","created":"2021-02-11","cited_by_count":117},{"id":"2005.10881","title":"Revisiting Membership Inference Under Realistic Assumptions","created":"2020-05-21","cited_by_count":112},{"id":"2110.03620","title":"Hyperparameter Tuning with Renyi Differential Privacy","created":"2021-10-07","cited_by_count":104},{"id":"2108.04978","title":"Winning the NIST Contest: A scalable and general approach to differentially private synthetic data","created":"2021-08-11","cited_by_count":102},{"id":"1808.06651","title":"Privacy Amplification by Iteration","created":"2018-08-20","cited_by_count":100},{"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":"2201.12677","title":"AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data","created":"2022-01-29","cited_by_count":90},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","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":"1812.06210","title":"A General Approach to Adding Differential Privacy to Iterative Training Procedures","created":"2018-12-15","cited_by_count":84},{"id":"2010.00906","title":"Quantifying Privacy Leakage in Graph Embedding","created":"2020-10-02","cited_by_count":82},{"id":"2112.09238","title":"Benchmarking Differentially Private Synthetic Data Generation Algorithms","created":"2021-12-16","cited_by_count":81},{"id":"1811.07971","title":"Private Selection from Private Candidates","created":"2018-11-19","cited_by_count":75},{"id":"2102.05855","title":"Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent","created":"2021-02-11","cited_by_count":73},{"id":"2110.04995","title":"The Skellam Mechanism for Differentially Private Federated Learning","created":"2021-10-11","cited_by_count":68},{"id":"2006.05535","title":"Locally Private Graph Neural Networks","created":"2020-06-09","cited_by_count":64},{"id":"1407.2674","title":"Private Learning and Sanitization: Pure vs. Approximate Differential Privacy","created":"2014-07-10","cited_by_count":63},{"id":"2205.13710","title":"Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss","created":"2022-05-27","cited_by_count":61},{"id":"2106.07153","title":"Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods","created":"2021-06-14","cited_by_count":59},{"id":"2202.08312","title":"Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams","created":"2022-02-16","cited_by_count":59},{"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":"2002.07772","title":"The Tree Ensemble Layer: Differentiability meets Conditional Computation","created":"2020-02-18","cited_by_count":57},{"id":"2104.07504","title":"Natural Language Understanding with Privacy-Preserving BERT","created":"2021-04-15","cited_by_count":55},{"id":"1811.10256","title":"Generalised Differential Privacy for Text Document Processing","created":"2018-11-26","cited_by_count":52},{"id":"2103.06641","title":"Differentially Private Query Release Through Adaptive Projection","created":"2021-03-11","cited_by_count":52},{"id":"2106.03408","title":"Antipodes of Label Differential Privacy: PATE and ALIBI","created":"2021-06-07","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":"1710.00901","title":"Prochlo: Strong Privacy for Analytics in the Crowd","created":"2017-10-02","cited_by_count":51},{"id":"2112.00193","title":"Public Data-Assisted Mirror Descent for Private Model Training","created":"2021-12-01","cited_by_count":49},{"id":"2211.06530","title":"Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning","created":"2022-11-12","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":"2106.13756","title":"Private Adaptive Gradient Methods for Convex Optimization","created":"2021-06-25","cited_by_count":46},{"id":"2201.12383","title":"Bounding Training Data Reconstruction in Private (Deep) Learning","created":"2022-01-28","cited_by_count":46},{"id":"2007.05453","title":"New Oracle-Efficient Algorithms for Private Synthetic Data Release","created":"2020-07-10","cited_by_count":43},{"id":"2111.15521","title":"Node-Level Differentially Private Graph Neural Networks","created":"2021-11-23","cited_by_count":43},{"id":"1510.01799","title":"Efficient Per-Example Gradient Computations","created":"2015-10-07","cited_by_count":42},{"id":"2001.03618","title":"Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation","created":"2020-01-10","cited_by_count":39},{"id":"2007.06605","title":"Privacy Amplification via Random Check-Ins","created":"2020-07-13","cited_by_count":39},{"id":"2202.05963","title":"Private Adaptive Optimization with Side Information","created":"2022-02-12","cited_by_count":38},{"id":"2206.04723","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","created":"2022-06-09","cited_by_count":38},{"id":"1911.10143","title":"Adversarial Learning of Privacy-Preserving and Task-Oriented Representations","created":"2019-11-22","cited_by_count":36},{"id":"2106.07830","title":"On the Convergence and Calibration of Deep Learning with Differential Privacy","created":"2021-06-15","cited_by_count":36},{"id":"2302.03098","title":"One-shot Empirical Privacy Estimation for Federated Learning","created":"2023-02-06","cited_by_count":36},{"id":"2202.07623","title":"Defending against Reconstruction Attacks with R\\'enyi Differential Privacy","created":"2022-02-15","cited_by_count":32},{"id":"2206.00846","title":"Faster Rates of Convergence to Stationary Points in Differentially Private Optimization","created":"2022-06-02","cited_by_count":32},{"id":"1802.05214","title":"Learning Privacy Preserving Encodings through Adversarial Training","created":"2018-02-14","cited_by_count":30}],"next_cursor":"100"}