Cover Image

Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Demelius, Lea, Kowald, Dominik, Kopeinik, Simone, Kern, Roman, Trügler, Andreas
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
by: Demelius, Lea, et al.
Published: (2023)

Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers
by: Semmelrock, Harald, et al.
Published: (2024)

RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
by: Feng, Ce, et al.
Published: (2024)

On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learning
by: Yang, Zhi, et al.
Published: (2025)

Establishing and Evaluating Trustworthy AI: Overview and Research Challenges
by: Kowald, Dominik, et al.
Published: (2024)

PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
by: Sha, Haichao, et al.
Published: (2023)

Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
by: Sander, Tom, et al.
Published: (2024)

DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
by: Wei, Jianxin, et al.
Published: (2022)

Differentially Private Generalized Linear Models Revisited
by: Arora, Raman, et al.
Published: (2022)

GeoClip: Geometry-Aware Clipping for Differentially Private SGD
by: Gilani, Atefeh, et al.
Published: (2025)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
by: Zhang, Xinwei, et al.
Published: (2023)

Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping
by: Zhao, Linzh, et al.
Published: (2025)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
by: Steinke, Thomas, et al.
Published: (2024)

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
by: Wei, Chengkun, et al.
Published: (2025)

Differentially Private Fair Binary Classifications
by: Ghoukasian, Hrad, et al.
Published: (2024)

Non-Asymptotic Analysis of Online Local Private Learning with SGD
by: Shi, Enze, et al.
Published: (2025)

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
by: Khah, Saleh Vatan, et al.
Published: (2025)

Revisiting Differentially Private Hyper-parameter Tuning
by: Xiang, Zihang, et al.
Published: (2024)

Disparate Impact on Group Accuracy of Linearization for Private Inference
by: Das, Saswat, et al.
Published: (2024)

How Private are DP-SGD Implementations?
by: Chua, Lynn, et al.
Published: (2024)

Multistakeholder Fairness in Tourism: What can Algorithms learn from Tourism Management?
by: Muellner, Peter, et al.
Published: (2025)

Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
by: Thakkar, Janvi, et al.
Published: (2024)

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
by: Liang, Hao, et al.
Published: (2025)

Differentially Private Post-Processing for Fair Regression
by: Xian, Ruicheng, et al.
Published: (2024)

Meta-Learning and Targeted Differential Privacy to Improve the Accuracy-Privacy Trade-off in Recommendations
by: Müllner, Peter, et al.
Published: (2026)

Balancing Utility and Privacy: Dynamically Private SGD with Random Projection
by: Jiang, Zhanhong, et al.
Published: (2025)

Privately Learning Decision Lists and a Differentially Private Winnow
by: Bun, Mark, et al.
Published: (2026)

Locally Differentially Private Online Federated Learning With Correlated Noise
by: Zhang, Jiaojiao, et al.
Published: (2024)

Bayesian Pseudo Posterior Mechanism for Differentially Private Machine Learning
by: Chew, Robert, et al.
Published: (2025)

Calibrating Practical Privacy Risks for Differentially Private Machine Learning
by: Gu, Yuechun, et al.
Published: (2024)

An Algorithm for Streaming Differentially Private Data
by: Kumar, Girish, et al.
Published: (2024)

Private and Communication-Efficient Federated Learning based on Differentially Private Sketches
by: Zhang, Meifan, et al.
Published: (2024)

Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
by: Kalinin, Nikita P., et al.
Published: (2025)

Differentially Private Learned Indexes
by: Du, Jianzhang, et al.
Published: (2024)

Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs
by: Hohensinner, Richard, et al.
Published: (2026)

Incentives in Private Collaborative Machine Learning
by: Sim, Rachael Hwee Ling, et al.
Published: (2024)

Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)
by: Bao, Wenxuan, et al.
Published: (2025)

Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

Online Sensitivity Optimization in Differentially Private Learning
by: Galli, Filippo, et al.
Published: (2023)

Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data
by: Yuan, Chih-Cheng Rex, et al.
Published: (2025)