arXiv Machine Learning June 2, 2026 By Haiyang Lu, Pratik Gajane, Shaojie Bai, Mohammad Sadegh Talebi

Randomized Least Squares Value Iteration itself is Joint Differentially Private

Read the original on arXiv Machine Learning →

arXiv:2606. 01952v1 Announce Type: new Abstract: As reinforcement learning (RL) increasingly applies to sensitive domains, such as health care and recommendation systems, privacy-preserving techniques have become essential to protect users' sensitive information.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 4

DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data

arXiv:2606. 04399v1 Announce Type: new Abstract: In the paradigm of decentralized learning, a group of agents collaborate to train a global model using distributed datasets without a central server.

By Yunsheng Yuan, Xue Xiao, Lina Wang, Feng Li

agents benchmarks safety

arXiv Machine Learning

Aug 4

When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence

arXiv:2603. 19040v2 Announce Type: replace Abstract: Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data.

By Chen Yaoling, Liang Hao, Tu Xiaotong

safety

arXiv Machine Learning

Jul 23

Differentially Private Neural Network Training Under the Hidden State Assumption

arXiv:2407. 08233v3 Announce Type: replace Abstract: Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over training steps, while aggregation-based approaches such as PATE suffer from data inefficiency due to disjoint data partitioning.

By Ding Chen, Haochen Luo, Xiaofei Wang, Chen Liu

benchmarks safety

arXiv Machine Learning

Jul 31

Quadratic Objective Perturbation: Curvature-Based Differential Privacy

arXiv:2605. 05905v2 Announce Type: replace Abstract: Objective perturbation is a standard mechanism in differentially private empirical risk minimization.

By Daniel Cortild, Coralia Cartis

safety

arXiv Machine Learning

Jun 15

Let's Ask Gauss: Improved One-Run Privacy Auditing

arXiv:2606. 12733v2 Announce Type: replace Abstract: Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guarantees hold in practice.

By Adya Agrawal, Yu Wei, Jaspal Singh, Malik Magdon-Ismail, Vassilis Zikas

safety

arXiv Machine Learning

Jul 28

DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton

arXiv:2607. 23649v1 Announce Type: new Abstract: Differential privacy provides formal privacy guarantees for training neural networks on sensitive data, while Bayesian deep learning offers a principled framework for uncertainty-aware prediction.

By Nour Jamoussi, Ikram Dridi, Giuseppe Serra, Marios Kountouris

safety

Related stories

DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data

When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence

Differentially Private Neural Network Training Under the Hidden State Assumption

Quadratic Objective Perturbation: Curvature-Based Differential Privacy

Let's Ask Gauss: Improved One-Run Privacy Auditing

DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton