Literature Database Entry

tao2026prose

Youming Tao, Shuzhen Chen, Zhangqing Zheng, Kai Li and Falko Dressler, "PROSE: Private Scalar-Exchange Federated Zeroth-Order Optimization," Proceedings of IEEE Annual Congress on Artificial Intelligence of Things (AioT 2026), Kobe, Japan, December 2026. (to appear)

Abstract

Resource-constrained ubiquitous IoT systems require collaborative learning methods that reduce both local training overhead and client communication while preserving data privacy. We propose PROSE (\emphPrivate Randomized Optimization via Scalar Exchange), a federated zeroth-order framework in which public random directions and locally privatized scalar coefficients jointly drive local optimization and client communication. The same privatized coefficients determine the local trajectory and are uploaded to the server, enabling exact reconstruction of the corresponding global updates under partial participation without model-dimensional client messages. We establish record-level differential privacy for the complete client-labeled server view and derive convergence guarantees for general smooth nonconvex objectives with multiple local updates and random directions. The analysis separates the effects of client sampling, local drift, direct privacy noise, query drift induced by earlier privatized updates, and zeroth-order smoothing. Experiments on MNIST and full-parameter OPT-125M fine-tuning across multiple privacy budgets show competitive private utility while reducing the defined client-uplink payload from model-dimensional updates to a small number of scalar coefficients, with orders-of-magnitude savings at language-model scale.

Quick access

BibTeX BibTeX

Contact

Youming Tao
Shuzhen Chen
Zhangqing Zheng
Kai Li
Falko Dressler

BibTeX reference

@inproceedings{tao2026prose,
    author = {Tao, Youming and Chen, Shuzhen and Zheng, Zhangqing and Li, Kai and Dressler, Falko},
    note = {to appear},
    title = {{PROSE: Private Scalar-Exchange Federated Zeroth-Order Optimization}},
    publisher = {IEEE},
    address = {Kobe, Japan},
    booktitle = {IEEE Annual Congress on Artificial Intelligence of Things (AioT 2026)},
    month = {12},
    year = {2026},
   }
   
   

Copyright notice

Links to final or draft versions of papers are presented here to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or distributed for commercial purposes without the explicit permission of the copyright holder.

The following applies to all papers listed above that have IEEE copyrights: Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

The following applies to all papers listed above that are in submission to IEEE conference/workshop proceedings or journals: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.

The following applies to all papers listed above that have ACM copyrights: ACM COPYRIGHT NOTICE. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Publications Dept., ACM, Inc., fax +1 (212) 869-0481, or permissions@acm.org.

The following applies to all SpringerLink papers listed above that have Springer Science+Business Media copyrights: The original publication is available at www.springerlink.com.

This page was automatically generated using BibDB and bib2web.

Last modified: 2026-10-27