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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 15

Privacy Preserving Gossip Learning

arXiv:2609.14778v1 Announce Type: new Abstract: We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are lear...

By Erkan Bayram, Mohamed-Ali Belabbas, Tamer Ba\c{s}ar

agents safety

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 31

Performative Privacy: When Differential Privacy Maximizes Utility

arXiv:2608.28198v1 Announce Type: new Abstract: Privacy-preserving learning is often motivated by the idea that protecting users' data can preserve trust and thus participation, improving utility in...

By Uddalak Mukherjee, Edwige Cyffers, Yann Chevaleyre

agents 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

One email a morning, machine-written

Related stories

Privacy Preserving Gossip Learning

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

Performative Privacy: When Differential Privacy Maximizes Utility

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