{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2109.12298","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","created":"2021-09-25","cited_by_count":383},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"id":"1808.00087","title":"Subsampled R\\'enyi Differential Privacy and Analytical Moments Accountant","created":"2018-07-31","cited_by_count":236},{"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":"2106.02848","title":"Numerical Composition of Differential Privacy","created":"2021-06-05","cited_by_count":180},{"id":"2006.15429","title":"Understanding Gradient Clipping in Private SGD: A Geometric Perspective","created":"2020-06-27","cited_by_count":142},{"id":"2002.03305","title":"Momentum Improves Normalized SGD","created":"2020-02-09","cited_by_count":139},{"id":"2007.14191","title":"Tempered Sigmoid Activations for Deep Learning with Differential Privacy","created":"2020-07-28","cited_by_count":122},{"id":"1911.11607","title":"Deep Learning with Gaussian Differential Privacy","created":"2019-11-26","cited_by_count":114},{"id":"1710.11029","title":"Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks","created":"2017-10-30","cited_by_count":109},{"id":"2110.03620","title":"Hyperparameter Tuning with Renyi Differential Privacy","created":"2021-10-07","cited_by_count":104},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","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":"1901.07931","title":"Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge","created":"2019-01-23","cited_by_count":86},{"id":"2106.08567","title":"Optimal Accounting of Differential Privacy via Characteristic Function","created":"2021-06-16","cited_by_count":86},{"id":"1908.07643","title":"AdaCliP: Adaptive Clipping for Private SGD","created":"2019-08-20","cited_by_count":77},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54},{"id":"1708.08694","title":"Natasha 2: Faster Non-Convex Optimization Than SGD","created":"2017-08-29","cited_by_count":49},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41},{"id":"2106.07830","title":"On the Convergence and Calibration of Deep Learning with Differential Privacy","created":"2021-06-15","cited_by_count":36},{"id":"1711.05224","title":"Revisiting Normalized Gradient Descent: Fast Evasion of Saddle Points","created":"2017-11-14","cited_by_count":29},{"id":"2102.03013","title":"Fast and Memory Efficient Differentially Private-SGD via JL Projections","created":"2021-02-05","cited_by_count":29},{"id":"2203.00324","title":"Differentially private training of residual networks with scale normalisation","created":"2022-03-01","cited_by_count":26},{"id":"2007.13985","title":"Stochastic Normalized Gradient Descent with Momentum for Large-Batch Training","created":"2020-07-28","cited_by_count":10},{"id":"2112.14430","title":"DP-FP: Differentially Private Forward Propagation for Large Models","created":"2021-12-29","cited_by_count":7},{"id":"2106.07094","title":"On the Convergence of Differentially Private Federated Learning on Non-Lipschitz Objectives, and with Normalized Client Updates","created":"2021-06-13","cited_by_count":5}],"next_cursor":null}