中文
相关论文

相关论文: Differentially Private Stochastic Optimization: Ne…

200 篇论文

We study differentially private (DP) algorithms for stochastic convex optimization: the problem of minimizing the population loss given i.i.d. samples from a distribution over convex loss functions. A recent work of Bassily et al. (2019)…

机器学习 · 计算机科学 2020-05-12 Vitaly Feldman , Tomer Koren , Kunal Talwar

Stochastic convex optimization over an $\ell_1$-bounded domain is ubiquitous in machine learning applications such as LASSO but remains poorly understood when learning with differential privacy. We show that, up to logarithmic factors the…

机器学习 · 计算机科学 2021-03-03 Hilal Asi , Vitaly Feldman , Tomer Koren , Kunal Talwar

Differentially private (DP) stochastic convex optimization (SCO) is a fundamental problem, where the goal is to approximately minimize the population risk with respect to a convex loss function, given a dataset of $n$ i.i.d. samples from a…

机器学习 · 计算机科学 2022-05-06 Raef Bassily , Cristóbal Guzmán , Anupama Nandi

We study differentially private (DP) algorithms for stochastic convex optimization (SCO). In this problem the goal is to approximately minimize the population loss given i.i.d. samples from a distribution over convex and Lipschitz loss…

机器学习 · 计算机科学 2019-08-28 Raef Bassily , Vitaly Feldman , Kunal Talwar , Abhradeep Thakurta

We introduce a new zeroth-order algorithm for private stochastic optimization on nonconvex and nonsmooth objectives. Given a dataset of size $M$, our algorithm ensures $(\alpha,\alpha\rho^2/2)$-R\'enyi differential privacy and finds a…

最优化与控制 · 数学 2024-07-01 Qinzi Zhang , Hoang Tran , Ashok Cutkosky

In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) in Euclidean and general $\ell_p^d$ spaces. Specifically, we focus on three settings that are still far from well understood: (1) DP-SCO…

机器学习 · 计算机科学 2023-04-03 Jinyan Su , Changhong Zhao , Di Wang

We study the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) with heavy-tailed data. Specifically, we focus on the $\ell_1$-norm linear regression in the $\epsilon$-DP model. While most of the previous work focuses…

机器学习 · 计算机科学 2022-01-11 Di Wang , Jinhui Xu

In this paper, we initiate a systematic investigation of differentially private algorithms for convex empirical risk minimization. Various instantiations of this problem have been studied before. We provide new algorithms and matching lower…

机器学习 · 计算机科学 2014-10-21 Raef Bassily , Adam Smith , Abhradeep Thakurta

In this paper, we consider the problem of designing Differentially Private (DP) algorithms for Stochastic Convex Optimization (SCO) on heavy-tailed data. The irregularity of such data violates some key assumptions used in almost all…

机器学习 · 计算机科学 2020-10-22 Di Wang , Hanshen Xiao , Srini Devadas , Jinhui Xu

We study differentially private (DP) algorithms for stochastic non-convex optimization. In this problem, the goal is to minimize the population loss over a $p$-dimensional space given $n$ i.i.d. samples drawn from a distribution. We improve…

机器学习 · 计算机科学 2020-08-12 Yingxue Zhou , Xiangyi Chen , Mingyi Hong , Zhiwei Steven Wu , Arindam Banerjee

We study the differentially private Empirical Risk Minimization (ERM) and Stochastic Convex Optimization (SCO) problems for non-smooth convex functions. We get a (nearly) optimal bound on the excess empirical risk and excess population loss…

机器学习 · 计算机科学 2021-03-31 Janardhan Kulkarni , Yin Tat Lee , Daogao Liu

We study the problem of $(\epsilon,\delta)$-differentially private learning of linear predictors with convex losses. We provide results for two subclasses of loss functions. The first case is when the loss is smooth and non-negative but not…

机器学习 · 计算机科学 2024-03-07 Raman Arora , Raef Bassily , Cristóbal Guzmán , Michael Menart , Enayat Ullah

Finding efficient, easily implementable differentially private (DP) algorithms that offer strong excess risk bounds is an important problem in modern machine learning. To date, most work has focused on private empirical risk minimization…

机器学习 · 计算机科学 2024-09-23 Andrew Lowy , Meisam Razaviyayn

Minimizing a convex risk function is the main step in many basic learning algorithms. We study protocols for convex optimization which provably leak very little about the individual data points that constitute the loss function.…

机器学习 · 计算机科学 2020-08-11 Di Wang , Adam Smith , Jinhui Xu

We study differentially private (DP) stochastic optimization (SO) with loss functions whose worst-case Lipschitz parameter over all data may be extremely large or infinite. To date, the vast majority of work on DP SO assumes that the loss…

机器学习 · 计算机科学 2024-10-01 Andrew Lowy , Meisam Razaviyayn

We study private stochastic convex optimization (SCO) under user-level differential privacy (DP) constraints. In this setting, there are $n$ users (e.g., cell phones), each possessing $m$ data items (e.g., text messages), and we need to…

机器学习 · 计算机科学 2024-10-25 Andrew Lowy , Daogao Liu , Hilal Asi

This paper focuses on the problem of Differentially Private Stochastic Optimization for (multi-layer) fully connected neural networks with a single output node. In the first part, we examine cases with no hidden nodes, specifically focusing…

机器学习 · 计算机科学 2023-10-13 Hanpu Shen , Cheng-Long Wang , Zihang Xiang , Yiming Ying , Di Wang

We study differentially private (DP) optimization algorithms for stochastic and empirical objectives which are neither smooth nor convex, and propose methods that return a Goldstein-stationary point with sample complexity bounds that…

机器学习 · 计算机科学 2025-06-10 Guy Kornowski , Daogao Liu , Kunal Talwar

We show that convex-concave Lipschitz stochastic saddle point problems (also known as stochastic minimax optimization) can be solved under the constraint of $(\epsilon,\delta)$-differential privacy with \emph{strong (primal-dual) gap} rate…

机器学习 · 计算机科学 2023-06-30 Raef Bassily , Cristóbal Guzmán , Michael Menart

One of the most effective algorithms for differentially private learning and optimization is objective perturbation. This technique augments a given optimization problem (e.g. deriving from an ERM problem) with a random linear term, and…

机器学习 · 计算机科学 2021-01-01 Seth Neel , Aaron Roth , Giuseppe Vietri , Zhiwei Steven Wu
‹ 上一页 1 2 3 10 下一页 ›