{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"2001.01523","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","created":"2020-01-06","cited_by_count":325},{"id":"1311.0776","title":"The Composition Theorem for Differential Privacy","created":"2013-11-04","cited_by_count":297},{"id":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"1905.03871","title":"Differentially Private Learning with Adaptive Clipping","created":"2019-05-09","cited_by_count":220},{"id":"1901.06053","title":"A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks","created":"2019-01-18","cited_by_count":214},{"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":"2006.04740","title":"The Heavy-Tail Phenomenon in SGD","created":"2020-06-08","cited_by_count":124},{"id":"2005.10785","title":"Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping","created":"2020-05-21","cited_by_count":104},{"id":"2110.02444","title":"Influence-Balanced Loss for Imbalanced Visual Classification","created":"2021-10-06","cited_by_count":91},{"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":"2206.07136","title":"Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger","created":"2022-06-14","cited_by_count":88},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86},{"id":"2302.13861","title":"Differentially Private Diffusion Models Generate Useful Synthetic Images","created":"2023-02-27","cited_by_count":86},{"id":"2305.01588","title":"Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees","created":"2023-05-02","cited_by_count":83},{"id":"1912.10985","title":"BackPACK: Packing more into backprop","created":"2019-12-23","cited_by_count":78},{"id":"1908.07643","title":"AdaCliP: Adaptive Clipping for Private SGD","created":"2019-08-20","cited_by_count":77},{"id":"2106.13673","title":"Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy","created":"2021-06-25","cited_by_count":69},{"id":"2007.14294","title":"A High Probability Analysis of Adaptive SGD with Momentum","created":"2020-07-28","cited_by_count":61},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54},{"id":"2010.11082","title":"On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data","created":"2020-10-21","cited_by_count":51},{"id":"2106.01336","title":"Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data","created":"2021-06-02","cited_by_count":47},{"id":"2106.03795","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks","created":"2021-06-07","cited_by_count":44},{"id":"1810.11059","title":"Uniform Convergence of Gradients for Non-Convex Learning and Optimization","created":"2018-10-25","cited_by_count":38},{"id":"2203.03106","title":"Differentially Private Federated Learning with Local Regularization and Sparsification","created":"2022-03-07","cited_by_count":36},{"id":"2206.13033","title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization","created":"2022-06-27","cited_by_count":36},{"id":"2102.10346","title":"Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance","created":"2021-02-20","cited_by_count":35},{"id":"2002.05685","title":"Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise","created":"2020-02-13","cited_by_count":33},{"id":"2006.05610","title":"High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise","created":"2020-06-10","cited_by_count":31},{"id":"2205.12900","title":"Pre-trained Perceptual Features Improve Differentially Private Image Generation","created":"2022-05-25","cited_by_count":28},{"id":"2207.07316","title":"Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain","created":"2022-07-15","cited_by_count":28},{"id":"2210.08371","title":"Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability","created":"2022-10-15","cited_by_count":25},{"id":"1910.09626","title":"Non-Gaussianity of Stochastic Gradient Noise","created":"2019-10-21","cited_by_count":22},{"id":"2109.05446","title":"Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation","created":"2021-09-12","cited_by_count":21},{"id":"2212.00328","title":"Differentially Private Learning with Per-Sample Adaptive Clipping","created":"2022-12-01","cited_by_count":21},{"id":"2306.06076","title":"Differentially Private Image Classification by Learning Priors from Random Processes","created":"2023-06-08","cited_by_count":19},{"id":"2201.12467","title":"Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters","created":"2022-01-29","cited_by_count":18},{"id":"2303.01256","title":"Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance","created":"2023-03-02","cited_by_count":16},{"id":"2003.13819","title":"Sharp Concentration Results for Heavy-Tailed Distributions","created":"2020-03-30","cited_by_count":15},{"id":"2311.14632","title":"Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach","created":"2023-11-24","cited_by_count":14},{"id":"2210.09634","title":"DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling","created":"2022-10-18","cited_by_count":13},{"id":"2102.07006","title":"Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections","created":"2021-02-13","cited_by_count":12},{"id":"1803.00195","title":"The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects","created":"2018-03-01","cited_by_count":9},{"id":"2112.00845","title":"Improving Differentially Private SGD via Randomly Sparsified Gradients","created":"2021-12-01","cited_by_count":8},{"id":"2204.08146","title":"PrivateRec: Differentially Private Training and Serving for Federated News Recommendation","created":"2022-04-18","cited_by_count":6},{"id":"2307.13680","title":"High Probability Analysis for Non-Convex Stochastic Optimization with Clipping","created":"2023-07-25","cited_by_count":5},{"id":"2312.03792","title":"PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance","created":"2023-12-06","cited_by_count":2}],"next_cursor":null}