English
Related papers

Related papers: Beyond Uniform Lipschitz Condition in Differential…

200 papers

Stochastic gradient descent ascent (SGDA) and its variants have been the workhorse for solving minimax problems. However, in contrast to the well-studied stochastic gradient descent (SGD) with differential privacy (DP) constraints, there is…

Machine Learning · Computer Science 2022-08-01 Zhenhuan Yang , Shu Hu , Yunwen Lei , Kush R. Varshney , Siwei Lyu , Yiming Ying

We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy (DP). Most prior work on this problem is restricted to the case where the loss function is Lipschitz. Instead, as introduced by…

Machine Learning · Computer Science 2022-11-02 Gautam Kamath , Xingtu Liu , Huanyu Zhang

Decentralized optimization has become a fundamental tool for large-scale learning systems; however, most existing methods rely on the classical Lipschitz smoothness assumption, which is often violated in problems with rapidly varying…

Optimization and Control · Mathematics 2026-01-08 Yanan Bo , Yongqiang Wang

We study stochastic convex optimization (SCO) with heavy-tailed gradients under pure $\varepsilon$-differential privacy (DP). Instead of assuming a bound on the worst-case Lipschitz parameter of the loss, we assume only a bounded $k$-th…

Machine Learning · Computer Science 2026-05-06 Andrew Lowy

Differentially Private Stochastic Gradient Descent (DP-SGD) is a widely adopted technique for privacy-preserving deep learning. A critical challenge in DP-SGD is selecting the optimal clipping threshold C, which involves balancing the…

Machine Learning · Computer Science 2025-04-02 Chengkun Wei , Weixian Li , Chen Gong , Wenzhi Chen

Per-example gradient clipping is a key algorithmic step that enables practical differential private (DP) training for deep learning models. The choice of clipping threshold R, however, is vital for achieving high accuracy under DP. We…

Machine Learning · Computer Science 2023-10-05 Zhiqi Bu , Yu-Xiang Wang , Sheng Zha , George Karypis

We establish matching upper and lower generalization error bounds for mini-batch Gradient Descent (GD) training with either deterministic or stochastic, data-independent, but otherwise arbitrary batch selection rules. We consider smooth…

Machine Learning · Computer Science 2023-10-24 Konstantinos E. Nikolakakis , Amin Karbasi , Dionysis Kalogerias

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)…

Machine Learning · Computer Science 2022-07-14 Prateek Varshney , Abhradeep Thakurta , Prateek Jain

Differentially Private Stochastic Gradient Descent (DP-SGD) is the dominant paradigm for private training, but its fundamental limitations under worst-case adversarial privacy definitions remain poorly understood. We analyze DP-SGD in the…

Machine Learning · Computer Science 2026-04-17 Murat Bilgehan Ertan , Marten van Dijk

Training large neural networks with meaningful/usable differential privacy security guarantees is a demanding challenge. In this paper, we tackle this problem by revisiting the two key operations in Differentially Private Stochastic…

Machine Learning · Computer Science 2022-10-11 Hanshen Xiao , Jun Wan , Srinivas Devadas

Gradient clipping is a popular modification to standard (stochastic) gradient descent, at every iteration limiting the gradient norm to a certain value $c >0$. It is widely used for example for stabilizing the training of deep learning…

Machine Learning · Computer Science 2023-11-10 Anastasia Koloskova , Hadrien Hendrikx , Sebastian U. Stich

In this work, we conduct a systematic study of stochastic saddle point problems (SSP) and stochastic variational inequalities (SVI) under the constraint of $(\epsilon,\delta)$-differential privacy (DP) in both Euclidean and non-Euclidean…

Machine Learning · Computer Science 2024-11-11 Raef Bassily , Cristóbal Guzmán , Michael Menart

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to protect sensitive data during the training of machine learning models, but its privacy guarantee often comes at a large cost of model performance due to the lack…

Machine Learning · Computer Science 2026-01-16 Hao Liang , Wanrong Zhang , Xinlei He , Kaishun Wu , Hong Xing

We study Stochastic Convex Optimization in the Differential Privacy model (DP-SCO). Unlike previous studies, here we assume the population risk function satisfies the Tsybakov Noise Condition (TNC) with some parameter $\theta>1$, where the…

Machine Learning · Computer Science 2025-09-08 Difei Xu , Meng Ding , Zihang Xiang , Jinhui Xu , Di Wang

Training differentially private machine learning models requires constraining an individual's contribution to the optimization process. This is achieved by clipping the $2$-norm of their gradient at a predetermined threshold prior to…

Machine Learning · Computer Science 2024-01-09 Filippo Galli , Catuscia Palamidessi , Tommaso Cucinotta

Privacy in AI remains a topic that draws attention from researchers and the general public in recent years. As one way to implement privacy-preserving AI, differentially private learning is a framework that enables AI models to use…

Machine Learning · Computer Science 2023-05-03 Tianyu Xia , Shuheng Shen , Su Yao , Xinyi Fu , Ke Xu , Xiaolong Xu , Xing Fu

Stochastic Gradient Descent (SGD) with gradient clipping is a powerful technique for enabling differentially private optimization. Although prior works extensively investigated clipping with a constant threshold, private training remains…

Machine Learning · Computer Science 2024-12-31 Egor Shulgin , Peter Richtárik

Differential Privacy (DP) provides a formal framework for training machine learning models with individual example level privacy. In the field of deep learning, Differentially Private Stochastic Gradient Descent (DP-SGD) has emerged as a…

Machine Learning · Computer Science 2022-05-24 Harsh Mehta , Abhradeep Thakurta , Alexey Kurakin , Ashok Cutkosky

We provide sharp path-dependent generalization and excess risk guarantees for the full-batch Gradient Descent (GD) algorithm on smooth losses (possibly non-Lipschitz, possibly nonconvex). At the heart of our analysis is an upper bound on…

Machine Learning · Statistics 2023-02-13 Konstantinos E. Nikolakakis , Farzin Haddadpour , Amin Karbasi , Dionysios S. Kalogerias

We develop new sub-optimality bounds for gradient descent (GD) that depend on the conditioning of the objective along the path of optimization rather than on global, worst-case constants. Key to our proofs is directional smoothness, a…

Machine Learning · Computer Science 2025-01-15 Aaron Mishkin , Ahmed Khaled , Yuanhao Wang , Aaron Defazio , Robert M. Gower