English
Related papers

Related papers: Private Zeroth-Order Optimization with Public Data

200 papers

This paper considers a consensus optimization problem, where all the nodes in a network, with access to the zeroth-order information of its local objective function only, attempt to cooperatively achieve a common minimizer of the sum of…

Optimization and Control · Mathematics 2024-06-17 Chengan Wang , Zichong Ou , Jie Lu

First-order algorithms have been popular for solving convex and non-convex optimization problems. A key assumption for the majority of these algorithms is that the gradient of the objective function is globally Lipschitz continuous, but…

Optimization and Control · Mathematics 2024-02-07 Junyu Zhang , Mingyi Hong

As the size of large language models grows exponentially, GPU memory has become a bottleneck for adapting these models to downstream tasks. In this paper, we aim to push the limits of memory-efficient training by minimizing memory usage on…

Machine Learning · Computer Science 2026-02-13 Sifeng Shang , Jiayi Zhou , Chenyu Lin , Minxian Li , Kaiyang Zhou

The problem of learning threshold functions is a fundamental one in machine learning. Classical learning theory implies sample complexity of $O(\xi^{-1} \log(1/\beta))$ (for generalization error $\xi$ with confidence $1-\beta$). The private…

Machine Learning · Computer Science 2022-11-14 Edith Cohen , Xin Lyu , Jelani Nelson , Tamás Sarlós , Uri Stemmer

We present differentially private (DP) algorithms for bilevel optimization, a problem class that received significant attention lately in various machine learning applications. These are the first algorithms for such problems under standard…

Machine Learning · Computer Science 2026-01-15 Guy Kornowski

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…

Machine Learning · Computer Science 2018-02-20 Aurélien Bellet , Rachid Guerraoui , Mahsa Taziki , Marc Tommasi

Fine-tuning large pre-trained LLMs generally demands extensive GPU memory. Traditional first-order optimizers like SGD encounter substantial difficulties due to increased memory requirements from storing activations and gradients during…

Machine Learning · Computer Science 2025-03-18 Liangyu Wang , Jie Ren , Hang Xu , Junxiao Wang , Huanyi Xie , David E. Keyes , Di Wang

Differentially Private Stochastic Gradients Descent (DP-SGD) is a prominent paradigm for preserving privacy in deep learning. It ensures privacy by perturbing gradients with random noise calibrated to their entire norm at each training…

Cryptography and Security · Computer Science 2024-06-06 Yixuan Liu , Li Xiong , Yuhan Liu , Yujie Gu , Ruixuan Liu , Hong Chen

Zeroth-order (ZO) optimization has become increasingly popular and important in fine-tuning large language models (LLMs), especially on edge devices due to its ability to adjust the model to local data without the need for memory-intensive…

Machine Learning · Computer Science 2026-05-18 Jiahe Chen , Ziye Ma

Machine learning models can leak information about the data used to train them. To mitigate this issue, Differentially Private (DP) variants of optimization algorithms like Stochastic Gradient Descent (DP-SGD) have been designed to…

Machine Learning · Computer Science 2022-10-24 Paul Mangold , Aurélien Bellet , Joseph Salmon , Marc Tommasi

Differential privacy is a widely accepted measure of privacy in the context of deep learning algorithms, and achieving it relies on a noisy training approach known as differentially private stochastic gradient descent (DP-SGD). DP-SGD…

Machine Learning · Computer Science 2023-07-26 Ce Feng , Nuo Xu , Wujie Wen , Parv Venkitasubramaniam , Caiwen Ding

In Semi-Supervised Semi-Private (SP) learning, the learner has access to both public unlabelled and private labelled data. We propose a computationally efficient algorithm that, under mild assumptions on the data, provably achieves…

Machine Learning · Computer Science 2023-06-08 Francesco Pinto , Yaxi Hu , Fanny Yang , Amartya Sanyal

The superior performance of large foundation models relies on the use of massive amounts of high-quality data, which often contain sensitive, private and copyrighted material that requires formal protection. While differential privacy (DP)…

Machine Learning · Computer Science 2024-10-30 Zhiqi Bu , Xinwei Zhang , Mingyi Hong , Sheng Zha , George Karypis

Fine-tuning large language models (LLMs) often faces GPU memory bottlenecks: the backward pass of first-order optimizers like Adam increases memory usage to more than 10 times the inference level (e.g., 633 GB for OPT-30B). Zeroth-order…

Machine Learning · Computer Science 2025-07-01 Sizhe Dang , Yangyang Guo , Yanjun Zhao , Haishan Ye , Xiaodong Zheng , Guang Dai , Ivor Tsang

We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of privacy loss random variables to quantify the privacy loss of DP…

Data Structures and Algorithms · Computer Science 2021-10-27 Sivakanth Gopi , Yin Tat Lee , Lukas Wutschitz

Obtaining high-quality data for collaborative training of machine learning models can be a challenging task due to A) regulatory concerns and B) a lack of data owner incentives to participate. The first issue can be addressed through the…

Machine Learning · Computer Science 2024-04-17 Dmitrii Usynin , Daniel Rueckert , Georgios Kaissis

Large language models (LLMs) have demonstrated impressive capabilities across numerous NLP tasks. Nevertheless, conventional first-order fine-tuning techniques impose heavy memory demands, creating practical obstacles to real-world…

Machine Learning · Computer Science 2025-05-27 Zhendong Mi , Qitao Tan , Xiaodong Yu , Zining Zhu , Geng Yuan , Shaoyi Huang

This paper considers the scenario that multiple data owners wish to apply a machine learning method over the combined dataset of all owners to obtain the best possible learning output but do not want to share the local datasets owing to…

Machine Learning · Computer Science 2019-07-09 Le Trieu Phong , Tran Thi Phuong

We consider the problem of differentially private (DP) convex empirical risk minimization (ERM). While the standard DP-SGD algorithm is theoretically well-established, practical implementations often rely on shuffled gradient methods that…

Machine Learning · Computer Science 2026-02-25 Shuli Jiang , Pranay Sharma , Zhiwei Steven Wu , Gauri Joshi

Recent works have shown that selecting an optimal model architecture suited to the differential privacy setting is necessary to achieve the best possible utility for a given privacy budget using differentially private stochastic gradient…

Machine Learning · Computer Science 2024-11-01 Anderson Santana de Oliveira , Caelin Kaplan , Khawla Mallat , Tanmay Chakraborty