English
Related papers

Related papers: Trade-off Functions for DP-SGD with Subsampling ba…

200 papers

In this paper, we study fluctuations of conditionally centered statistics of the form $$N^{-1/2}\sum_{i=1}^N c_i(g(\sigma_i)-\mathbb{E}_N[g(\sigma_i)|\sigma_j,j\neq i])$$ where $(\sigma_1,\ldots ,\sigma_N)$ are sampled from a dependent…

Statistics Theory · Mathematics 2025-10-07 Nabarun Deb

(Gradient) Expectation Maximization (EM) is a widely used algorithm for estimating the maximum likelihood of mixture models or incomplete data problems. A major challenge facing this popular technique is how to effectively preserve the…

Machine Learning · Computer Science 2022-01-19 Di Wang , Jiahao Ding , Lijie Hu , Zejun Xie , Miao Pan , Jinhui Xu

We prove new upper and lower bounds on the sample complexity of $(\epsilon, \delta)$ differentially private algorithms for releasing approximate answers to threshold functions. A threshold function $c_x$ over a totally ordered domain $X$…

Cryptography and Security · Computer Science 2024-12-23 Mark Bun , Kobbi Nissim , Uri Stemmer , Salil Vadhan

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

Differentially Private Stochastic Gradient Descent (DP-SGD) is a key method for applying privacy in the training of deep learning models. It applies isotropic Gaussian noise to gradients during training, which can perturb these gradients in…

Machine Learning · Computer Science 2023-11-28 Pedro Faustini , Natasha Fernandes , Shakila Tonni , Annabelle McIver , Mark Dras

In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training. (Here, public data refers to auxiliary data sets that have no privacy…

We revisit the classical problem of finding an approximately stationary point of the average of $n$ smooth and possibly nonconvex functions. The optimal complexity of stochastic first-order methods in terms of the number of gradient…

Machine Learning · Computer Science 2022-06-07 Alexander Tyurin , Lukang Sun , Konstantin Burlachenko , Peter Richtárik

Thanks to the reparameterization trick, deep latent Gaussian models have shown tremendous success recently in learning latent representations. The ability to couple them however with nonparamet-ric priors such as the Dirichlet Process (DP)…

Machine Learning · Statistics 2020-07-28 Amine Echraibi , Joachim Flocon-Cholet , Stéphane Gosselin , Sandrine Vaton

A long-standing problem in the theory of stochastic gradient descent (SGD) is to prove that its without-replacement version RandomShuffle converges faster than the usual with-replacement version. We present the first (to our knowledge)…

Optimization and Control · Mathematics 2019-10-09 Jeff Z. HaoChen , Suvrit Sra

This paper provides a framework to analyze stochastic gradient algorithms in a mean squared error (MSE) sense using the asymptotic normality result of the stochastic gradient descent (SGD) iterates. We perform this analysis by taking the…

Machine Learning · Statistics 2019-10-28 Yakup Ceki Papo

We study person-level differentially private (DP) mean estimation in the case where each person holds multiple samples. DP here requires the usual notion of distributional stability when $\textit{all}$ of a person's datapoints can be…

Data Structures and Algorithms · Computer Science 2024-07-22 Sushant Agarwal , Gautam Kamath , Mahbod Majid , Argyris Mouzakis , Rose Silver , Jonathan Ullman

This paper studies how to learn variational autoencoders with a variety of divergences under differential privacy constraints. We often build a VAE with an appropriate prior distribution to describe the desired properties of the learned…

Machine Learning · Computer Science 2020-06-22 Tsubasa Takahashi , Shun Takagi , Hajime Ono , Tatsuya Komatsu

Many problems in trustworthy ML can be formulated as minimization of the model error under constraints on the prediction rates of the model for suitably-chosen marginals, including most group fairness constraints (demographic parity,…

Machine Learning · Computer Science 2025-05-30 Mohammad Yaghini , Tudor Cebere , Michael Menart , Aurélien Bellet , Nicolas Papernot

Empirical process theory for i.i.d. observations has emerged as a ubiquitous tool for understanding the generalization properties of various statistical problems. However, in many applications where the data exhibit temporal dependencies…

Statistics Theory · Mathematics 2024-01-18 Nabarun Deb , Debarghya Mukherjee

Shuffler-based differential privacy (shuffle-DP) is a privacy paradigm providing high utility by involving a shuffler to permute noisy report from users. Existing shuffle-DP protocols mainly focus on the design of shuffler-based categorical…

Cryptography and Security · Computer Science 2026-03-06 Xiaoguang Li , Hanyi Wang , Yaowei Huang , Jungang Yang , Qingqing Ye , Haonan Yan , Ke Pan , Zhe Sun , Hui Li

Federated learning (FL) is a new paradigm that enables many clients to jointly train a machine learning (ML) model under the orchestration of a parameter server while keeping the local data not being exposed to any third party. However, the…

Machine Learning · Computer Science 2022-04-27 Yiwei Li , Shuai Wang , Tsung-Hui Chang , Chong-Yung Chi

In this work, we conduct the first systematic study of stochastic variational inequality (SVI) and stochastic saddle point (SSP) problems under the constraint of differential privacy (DP). We propose two algorithms: Noisy Stochastic…

Optimization and Control · Mathematics 2022-04-04 Digvijay Boob , Cristóbal Guzmán

Posterior sampling, i.e., exponential mechanism to sample from the posterior distribution, provides $\varepsilon$-pure differential privacy (DP) guarantees and does not suffer from potentially unbounded privacy breach introduced by…

Machine Learning · Computer Science 2024-05-02 Yingyu Lin , Yi-An Ma , Yu-Xiang Wang , Rachel Redberg , Zhiqi Bu

In the setting of entangled single-sample distributions, the goal is to estimate some common parameter shared by a family of $n$ distributions, given one single sample from each distribution. This paper studies mean estimation for entangled…

Machine Learning · Computer Science 2020-07-14 Yingyu Liang , Hui Yuan

We introduce a multiple target optimization framework for DP-SGD referred to as pro-active DP. In contrast to traditional DP accountants, which are used to track the expenditure of privacy budgets, the pro-active DP scheme allows one to…

Machine Learning · Computer Science 2024-06-05 Marten van Dijk , Nhuong V. Nguyen , Toan N. Nguyen , Lam M. Nguyen , Phuong Ha Nguyen