English
Related papers

Related papers: Differentially Private Accelerated Optimization Al…

200 papers

We propose a new method for unconstrained optimization of a smooth and strongly convex function, which attains the optimal rate of convergence of Nesterov's accelerated gradient descent. The new algorithm has a simple geometric…

Optimization and Control · Mathematics 2015-06-30 Sébastien Bubeck , Yin Tat Lee , Mohit Singh

Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks,…

Machine Learning · Computer Science 2023-11-30 Jie Fu , Qingqing Ye , Haibo Hu , Zhili Chen , Lulu Wang , Kuncan Wang , Xun Ran

This work studies the distributed empirical risk minimization (ERM) problem under differential privacy (DP) constraint. Standard distributed algorithms achieve DP typically by perturbing all local subgradients with noise, leading to…

Optimization and Control · Mathematics 2023-07-04 Changxin Liu , Karl H. Johansson , Yang Shi

Differential privacy (DP) techniques can be applied to the federated learning model to statistically guarantee data privacy against inference attacks to communication among the learning agents. While ensuring strong data privacy, however,…

Machine Learning · Computer Science 2022-02-22 Minseok Ryu , Kibaek Kim

Iterative algorithms for differential privacy run for a fixed number of iterations, where each iteration learns some information from data and produces an intermediate output. However, the algorithm only releases the output of the last…

Data Structures and Algorithms · Computer Science 2016-09-13 Jaewoo Lee , Daniel Kifer

With changes in privacy laws, there is often a hard requirement for client data to remain on the device rather than being sent to the server. Therefore, most processing happens on the device, and only an altered element is sent to the…

Cryptography and Security · Computer Science 2022-12-27 Ajinkya K Mulay

We consider a gradient approximation scheme that is based on applying needle shaped inputs. By using ideas known from the classic proof of the Pontryagin Maximum Principle we derive an approximation that reveals that the considered system…

Systems and Control · Computer Science 2016-03-15 Simon Michalowsky , Christian Ebenbauer

There has been significant interest in generalizations of the Nesterov accelerated gradient descent algorithm due to its improved performance guarantee compared to the standard gradient descent algorithm, and its applicability to large…

Optimization and Control · Mathematics 2021-03-29 Taeyoung Lee , Molei Tao , Melvin Leok

Differentially private (DP) optimization is the standard paradigm to learn large neural networks that are accurate and privacy-preserving. The computational cost for DP deep learning, however, is notoriously heavy due to the per-sample…

Machine Learning · Computer Science 2023-09-20 Zhiqi Bu , Yu-Xiang Wang , Sheng Zha , George Karypis

We study instrumental variable regression (IVaR) under differential privacy constraints. Classical IVaR methods (like two-stage least squares regression) rely on solving moment equations that directly use sensitive covariates and…

Machine Learning · Statistics 2026-02-17 Haodong Liang , Yanhao Jin , Krishnakumar Balasubramanian , Lifeng Lai

Nesterov's accelerated gradient descent method (AGD) is a seminal deterministic first-order method known to achieve the optimal order of iteration complexity for solving convex smooth optimization problems. Two distinct sequences of…

Optimization and Control · Mathematics 2026-03-10 Yan Wu , Yipeng Zhang , Lu Liu , Yuyuan Ouyang

Differential privacy (DP) provides robust privacy guarantees for statistical inference, but this can lead to unreliable results and biases in downstream applications. While several noise-aware approaches have been proposed which integrate…

Machine Learning · Statistics 2026-05-29 Talal Alrawajfeh , Joonas Jälkö , Antti Honkela

We study learning properties of accelerated gradient descent methods for linear least-squares in Hilbert spaces. We analyze the implicit regularization properties of Nesterov acceleration and a variant of heavy-ball in terms of…

Machine Learning · Computer Science 2019-12-17 Nicolò Pagliana , Lorenzo Rosasco

In this paper, we generalize the well-known Nesterov's accelerated gradient (AG) method, originally designed for convex smooth optimization, to solve nonconvex and possibly stochastic optimization problems. We demonstrate that by properly…

Optimization and Control · Mathematics 2013-10-15 Saeed Ghadimi , Guanghui Lan

Privacy issues of recommender systems have become a hot topic for the society as such systems are appearing in every corner of our life. In contrast to the fact that many secure multi-party computation protocols have been proposed to…

Cryptography and Security · Computer Science 2017-03-13 Jun Wang , Qiang Tang

We analyze the convergence rate of a family of inertial algorithms, which can be obtained by discretization of an inertial system with Hessian-driven damping. We recover a convergence rate, up to a factor of 2 speedup upon Nesterov's…

Optimization and Control · Mathematics 2025-02-25 Zepeng Wang , Juan Peypouquet

Gradient clipping is a fundamental tool in Deep Learning, improving the high-probability convergence of stochastic first-order methods like SGD, AdaGrad, and Adam under heavy-tailed noise, which is common in training large language models.…

Machine Learning · Computer Science 2025-09-30 Saleh Vatan Khah , Savelii Chezhegov , Shahrokh Farahmand , Samuel Horváth , Eduard Gorbunov

In this work, we propose new adaptive step size strategies that improve several stochastic gradient methods. Our first method (StoPS) is based on the classical Polyak step size (Polyak, 1987) and is an extension of the recent development of…

Machine Learning · Computer Science 2022-08-11 Samuel Horváth , Konstantin Mishchenko , Peter Richtárik

We present and analyze a momentum-based gradient method for training linear classifiers with an exponentially-tailed loss (e.g., the exponential or logistic loss), which maximizes the classification margin on separable data at a rate of…

Machine Learning · Computer Science 2021-08-24 Ziwei Ji , Nathan Srebro , Matus Telgarsky

Network routing problems are common across many engineering applications. Computing optimal routing policies requires knowledge about network demand, i.e., the origin and destination (OD) of all requests in the network. However, privacy…

Systems and Control · Electrical Eng. & Systems 2022-10-27 Matthew Tsao , Karthik Gopalakrishnan , Kaidi Yang , Marco Pavone