English
Related papers

Related papers: Private Stochastic Convex Optimization with Optima…

200 papers

Decentralized learning has emerged as a powerful approach for handling large datasets across multiple machines in a communication-efficient manner. However, such methods often face scalability limitations, as increasing the number of…

Machine Learning · Computer Science 2025-06-03 Ofri Eisen , Ron Dorfman , Kfir Y. Levy

We are interested in privatizing an approximate posterior inference algorithm called Expectation Propagation (EP). EP approximates the posterior by iteratively refining approximations to the local likelihoods, and is known to provide better…

Machine Learning · Computer Science 2022-11-02 Margarita Vinaroz , Mijung Park

The problem of estimating a parameter in the drift coefficient is addressed for $N$ discretely observed independent and identically distributed stochastic differential equations (SDEs). This is done considering additional constraints,…

Statistics Theory · Mathematics 2024-10-17 Chiara Amorino , Arnaud Gloter , Hélène Halconruy

Decentralized optimization, particularly the class of decentralized composite convex optimization (DCCO) problems, has found many applications. Due to ubiquitous communication congestion and random dropouts in practice, it is highly…

Optimization and Control · Mathematics 2022-10-12 Changxin Liu , Zirui Zhou , Jian Pei , Yong Zhang , Yang Shi

We consider the privacy amplification properties of a sampling scheme in which a user's data is used in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps. This sampling scheme has been recently applied in the…

Machine Learning · Computer Science 2026-02-20 Vitaly Feldman , Moshe Shenfeld

Convex programming with linear constraints plays an important role in the operation of a number of everyday systems. However, absent any additional protections, revealing or acting on the solutions to such problems may reveal information…

Optimization and Control · Mathematics 2024-09-16 Alexander Benvenuti , Brendan Bialy , Miriam Dennis , Matthew Hale

We introduce a novel framework for differentially private (DP) statistical estimation via data truncation, addressing a key challenge in DP estimation when the data support is unbounded. Traditional approaches rely on problem-specific…

Machine Learning · Computer Science 2025-11-11 Manolis Zampetakis , Felix Zhou

In this paper, we discuss an application of the SDDP type algorithm to nested risk-averse formulations of Stochastic Optimal Control (SOC) problems. We propose a construction of a statistical upper bound for the optimal value of risk-averse…

Optimization and Control · Mathematics 2023-05-04 Vincent Guigues , Alexander Shapiro , Yi Cheng

We introduce a differentially private (DP) algorithm called reveal-or-obscure (ROO) to generate a single representative sample from a dataset of $n$ observations drawn i.i.d. from an unknown discrete distribution $P$. Unlike methods that…

Information Theory · Computer Science 2026-02-18 Naima Tasnim , Atefeh Gilani , Lalitha Sankar , Oliver Kosut

This paper considers the problem of minimizing an expectation function over a closed convex set, coupled with a {\color{black} functional or expectation} constraint on either decision variables or problem parameters. We first present a new…

Optimization and Control · Mathematics 2020-10-05 Guanghui Lan , Zhiqiang Zhou

We study the problem of sampling from a distribution under local differential privacy (LDP). Given a private distribution $P \in \mathcal{P}$, the goal is to generate a single sample from a distribution that remains close to $P$ in…

Machine Learning · Computer Science 2025-10-13 Hrad Ghoukasian , Bonwoo Lee , Shahab Asoodeh

Many algorithms have been developed to estimate probability distributions subject to differential privacy (DP): such an algorithm takes as input independent samples from a distribution and estimates the density function in a way that is…

Cryptography and Security · Computer Science 2024-12-17 Albert Cheu , Debanuj Nayak

This paper considers stochastic weakly convex optimization without the standard Lipschitz continuity assumption. Based on new adaptive regularization (stepsize) strategies, we show that a wide class of stochastic algorithms, including the…

Optimization and Control · Mathematics 2024-11-07 Wenzhi Gao , Qi Deng

By enabling multiple agents to cooperatively solve a global optimization problem in the absence of a central coordinator, decentralized stochastic optimization is gaining increasing attention in areas as diverse as machine learning,…

Optimization and Control · Mathematics 2022-08-10 Yongqiang Wang , Tamer Basar

Local differential privacy (LDP) is increasingly employed in privacy-preserving machine learning to protect user data before sharing it with an untrusted aggregator. Most LDP methods assume that users possess only a single data record,…

Machine Learning · Computer Science 2025-05-05 Behnoosh Zamanlooy , Mario Diaz , Shahab Asoodeh

One of the major bottlenecks for deploying popular first-order differentially private (DP) machine learning algorithms (e.g., DP-SGD) lies in their high computation and memory cost, despite the existence of optimized implementations.…

Machine Learning · Computer Science 2026-01-14 Xuchen Gong , Tian Li

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…

Optimization and Control · Mathematics 2024-07-01 Qinzi Zhang , Hoang Tran , Ashok Cutkosky

We consider a distributed learning setup where a sparse signal is estimated over a network. Our main interest is to save communication resource for information exchange over the network and reduce processing time. Each node of the network…

Machine Learning · Statistics 2018-04-03 Ahmed Zaki , Saikat Chatterjee , Partha P. Mitra , Lars K. Rasmussen

The concept of differential privacy (DP) can quantitatively measure privacy loss by observing the changes in the distribution caused by the inclusion of individuals in the target dataset. The DP, which is generally used as a constraint, has…

Cryptography and Security · Computer Science 2025-07-16 Sehyun Ryu , Jonggyu Jang , Hyun Jong Yang

Multi-epoch, small-batch, Stochastic Gradient Descent (SGD) has been the method of choice for learning with large over-parameterized models. A popular theory for explaining why SGD works well in practice is that the algorithm has an…

Machine Learning · Computer Science 2021-07-13 Satyen Kale , Ayush Sekhari , Karthik Sridharan