English
Related papers

Related papers: DP-Muon: Differentially Private Optimization via M…

200 papers

Muon has recently emerged as a strong optimizer for large language model pre-training, orthogonalizing the momentum matrix via Newton--Schulz polar iterations. A natural intuition is that polar iterations, by flattening the singular…

Machine Learning · Computer Science 2026-05-15 Ruijie Zhang , Yequan Zhao , Ziyue Liu , Zhengyang Wang , Yupeng Su , Liyan Tan , Zheng Zhang

Orthogonal momentum gradient updates have emerged to overcome the limitations of vector-based optimizers like Adam. The vector-based optimizer Adam suffers from high memory costs and ill-conditioned momentum gradient updates. However,…

Machine Learning · Computer Science 2025-12-19 Dipan Maity

Differentially Private Stochastic Gradient Descent (DP-SGD) is a cornerstone technique for ensuring privacy in deep learning, widely used in both training from scratch and fine-tuning large-scale language models. While DP-SGD predominantly…

Cryptography and Security · Computer Science 2026-03-10 Meisam Mohammady , Qin Yang , Nicholas Stout , Ayesha Samreen , Han Wang , Christopher J Quinn , Yuan Hong

Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at…

Machine Learning · Computer Science 2022-11-09 Franziska Boenisch , Christopher Mühl , Roy Rinberg , Jannis Ihrig , Adam Dziedzic

The vanilla Differentially-Private Stochastic Gradient Descent (DP-SGD), including DP-Adam and other variants, ensures the privacy of training data by uniformly distributing privacy costs across training steps. The equivalent privacy costs…

Machine Learning · Computer Science 2022-01-19 Jian Du , Song Li , Xiangyi Chen , Siheng Chen , Mingyi Hong

In this paper, we study the problem of (finite sum) minimax optimization in the Differential Privacy (DP) model. Unlike most of the previous studies on the (strongly) convex-concave settings or loss functions satisfying the…

Machine Learning · Computer Science 2025-03-25 Ruijia Zhang , Mingxi Lei , Meng Ding , Zihang Xiang , Jinhui Xu , Di Wang

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…

Machine Learning · Computer Science 2024-10-10 Dmitrii Avdiukhin , Michael Dinitz , Chenglin Fan , Grigory Yaroslavtsev

Muon and related normalized optimizers decouple the choice of update direction from the choice of step scale, but their practical performance remains sensitive to the scale of the normalized step. We study adaptive scaling rules for Muon in…

Machine Learning · Computer Science 2026-05-20 Yury Demidovich , Abhishek Chakraborty , Grigory Malinovsky , Angelia Nedić , Peter Richtárik

Differentially private stochastic gradient descent (DP-SGD) enables private deep learning through per-example clipping and calibrated Gaussian noise, but its high-variance updates can reduce utility on challenging datasets. We propose…

Machine Learning · Computer Science 2026-05-21 Mohammad Partohaghighi , Roummel Marcia

Stochastic optimization is a pivotal enabler in modern machine learning, producing effective models for various tasks. However, several existing works have shown that model parameters and gradient information are susceptible to privacy…

Machine Learning · Computer Science 2025-09-15 Zhanhong Jiang , Md Zahid Hasan , Nastaran Saadati , Aditya Balu , Chao Liu , Soumik Sarkar

Strong Differential Privacy (DP) and Optimization guarantees are two desirable properties for a method in Federated Learning (FL). However, existing algorithms do not achieve both properties at once: they either have optimal DP guarantees…

Machine Learning · Computer Science 2026-03-06 Rustem Islamov , Samuel Horvath , Aurelien Lucchi , Peter Richtarik , Eduard Gorbunov

When training a machine learning model with differential privacy, one sets a privacy budget. This budget represents a maximal privacy violation that any user is willing to face by contributing their data to the training set. We argue that…

Machine Learning · Computer Science 2024-01-22 Franziska Boenisch , Christopher Mühl , Adam Dziedzic , Roy Rinberg , Nicolas Papernot

Muon is a recently proposed optimizer that enforces orthogonality in parameter updates by projecting gradients onto the Stiefel manifold, leading to stable and efficient training in large-scale deep neural networks. Meanwhile, the…

Machine Learning · Computer Science 2026-03-18 Hideaki Iiduka

In this paper, we introduce a new notion of guaranteed privacy that requires that the change of the range of the corresponding inclusion function to the true function is small. In particular, leveraging mixed-monotone inclusion functions,…

Optimization and Control · Mathematics 2022-09-26 Mohammad Khajenejad , Sonia Martinez

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

The majority of parameters in neural networks are naturally represented as matrices. However, most commonly used optimizers treat these matrix parameters as flattened vectors during optimization, potentially overlooking their inherent…

Machine Learning · Statistics 2026-04-15 Wei Shen , Ruichuan Huang , Minhui Huang , Cong Shen , Jiawei Zhang

Distributed training of large neural networks is bottlenecked by full-precision gradient communication and by coordinatewise optimizers that ignore the matrix structure of weight tensors. We propose Sign-Muon, a 1-bit, matrix-aware…

Machine Learning · Computer Science 2026-05-19 Neel Mishra , Kushagara Trivedi , Pawan Kumar

As a prevailing collaborative filtering method for recommendation systems, one-bit matrix completion requires data collected by users to provide personalized service. Due to insidious attacks and unexpected inference, the release of users'…

Cryptography and Security · Computer Science 2022-06-09 Zhengpin Li , Zheng Wei , Zengfeng Huang , Xiaojun Mao , Jian Wang

This study addresses the issues of privacy protection and efficiency in instruction fine-tuning of large-scale language models by proposing a parameter-efficient method that integrates differential privacy noise allocation with gradient…

Computation and Language · Computer Science 2025-12-09 Yulin Huang , Yaxuan Luan , Jinxu Guo , Xiangchen Song , Yuchen Liu

Training machine learning models with differential privacy (DP) has received increasing interest in recent years. One of the most popular algorithms for training differentially private models is differentially private stochastic gradient…

Machine Learning · Computer Science 2024-02-21 Ziteng Sun , Ananda Theertha Suresh , Aditya Krishna Menon
‹ Prev 1 4 5 6 7 8 10 Next ›