中文
相关论文

相关论文: Fast Dimension Independent Private AdaGrad on Publ…

200 篇论文

As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient…

机器学习 · 计算机科学 2023-11-15 Badih Ghazi , Yangsibo Huang , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Amer Sinha , Chiyuan Zhang

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

Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsampling, Gaussian perturbation, and privacy accounting. Classical DP-SGD releases a noisy…

密码学与安全 · 计算机科学 2026-05-12 Mohammad Partohaghighi , Roummel Marcia

Although there exist plentiful theories of empirical risk minimization (ERM) for supervised learning, current theoretical understandings of ERM for a related problem---stochastic convex optimization (SCO), are limited. In this work, we…

机器学习 · 计算机科学 2017-02-08 Lijun Zhang , Tianbao Yang , Rong Jin

In this work, we investigate the margin-maximization bias exhibited by gradient-based algorithms in classifying linearly separable data. We present an in-depth analysis of the specific properties of the velocity field associated with…

机器学习 · 计算机科学 2024-12-30 Mingze Wang , Zeping Min , Lei Wu

We derive bounds on the sample complexity of empirical risk minimization (ERM) in the context of minimizing non-convex risks that admit the strict saddle property. Recent progress in non-convex optimization has yielded efficient algorithms…

机器学习 · 计算机科学 2017-06-06 Alon Gonen , Shai Shalev-Shwartz

In this paper, we study the Empirical Risk Minimization (ERM) problem in the non-interactive Local Differential Privacy (LDP) model. Previous research on this problem \citep{smith2017interaction} indicates that the sample complexity, to…

机器学习 · 计算机科学 2020-11-12 Di Wang , Marco Gaboardi , Adam Smith , Jinhui Xu

We propose an adaptive (stochastic) gradient perturbation method for differentially private empirical risk minimization. At each iteration, the random noise added to the gradient is optimally adapted to the stepsize; we name this process…

机器学习 · 计算机科学 2021-10-26 Xiaoxia Wu , Lingxiao Wang , Irina Cristali , Quanquan Gu , Rebecca Willett

A parametric class of trust-region algorithms for unconstrained nonconvex optimization is considered where the value of the objective function is never computed. The class contains a deterministic version of the first-order Adagrad method…

最优化与控制 · 数学 2023-06-08 S. Gratton , S. Jerad , Ph. L. Toint

We propose a general optimization-based framework for computing differentially private M-estimators and a new method for constructing differentially private confidence regions. Firstly, we show that robust statistics can be used in…

统计理论 · 数学 2023-12-14 Marco Avella-Medina , Casey Bradshaw , Po-Ling Loh

Speech enhancement (SE) is proved effective in reducing noise from noisy speech signals for downstream automatic speech recognition (ASR), where multi-task learning strategy is employed to jointly optimize these two tasks. However, the…

音频与语音处理 · 电气工程与系统科学 2023-05-04 Yuchen Hu , Chen Chen , Ruizhe Li , Qiushi Zhu , Eng Siong Chng

Stochastic gradient descent (SGD) is a simple and popular method to solve stochastic optimization problems which arise in machine learning. For strongly convex problems, its convergence rate was known to be O(\log(T)/T), by running SGD for…

机器学习 · 计算机科学 2015-03-19 Alexander Rakhlin , Ohad Shamir , Karthik Sridharan

It has been observed in a variety of contexts that gradient descent methods have great success in solving low-rank matrix factorization problems, despite the relevant problem formulation being non-convex. We tackle a particular instance of…

数值分析 · 计算机科学 2016-06-28 Dejiao Zhang , Laura Balzano

Sparsity regularized loss minimization problems play an important role in various fields including machine learning, data mining, and modern statistics. Proximal gradient descent method and coordinate descent method are the most popular…

机器学习 · 计算机科学 2023-11-13 Runxue Bao , Bin Gu , Heng Huang

The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much attention in recent years, in the form of algorithms and…

机器学习 · 计算机科学 2013-04-30 Ohad Shamir

We study the trade-offs between convergence rate and robustness to gradient errors in designing a first-order algorithm. We focus on gradient descent (GD) and accelerated gradient (AG) methods for minimizing strongly convex functions when…

最优化与控制 · 数学 2019-11-07 Necdet Serhat Aybat , Alireza Fallah , Mert Gurbuzbalaban , Asuman Ozdaglar

Private optimization is a topic of major interest in machine learning, with differentially private stochastic gradient descent (DP-SGD) playing a key role in both theory and practice. Furthermore, DP-SGD is known to be a powerful tool in…

机器学习 · 计算机科学 2024-10-10 Dmitrii Avdiukhin , Michael Dinitz , Chenglin Fan , Grigory Yaroslavtsev

We study the problem of online generalized linear regression in the stochastic setting, where the label is generated from a generalized linear model with possibly unbounded additive noise. We provide a sharp analysis of the classical…

机器学习 · 计算机科学 2023-03-28 Heyang Zhao , Dongruo Zhou , Jiafan He , Quanquan Gu

We study the problem of differentially private linear regression where each data point is sampled from a fixed sub-Gaussian style distribution. We propose and analyze a one-pass mini-batch stochastic gradient descent method (DP-AMBSSGD)…

机器学习 · 计算机科学 2022-07-14 Prateek Varshney , Abhradeep Thakurta , Prateek Jain

Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This has motivated a…

机器学习 · 统计学 2019-02-28 Xiaoyu Li , Francesco Orabona