paper-with-me

홈 › Papers

Online Learning with Adversaries: A Differential-Inclusion Analysis

2023-04-04 · Swetha Ganesh, Alexandre Reiffers-Masson, Gugan Thoppe

We introduce an observation-matrix-based framework for fully asynchronous online Federated Learning (FL) with adversaries. In this work, we demonstrate its effectiveness in estimating the mean of a random vector. Our main result is that the proposed algorithm almost surely converges to the desired mean $\mu.$ This makes ours the first asynchronous FL method to have an a.s. convergence guarantee in the presence of adversaries. We derive this convergence using a novel differential-inclusion-based two-timescale analysis. Two other highlights of our proof include (a) the use of a novel Lyapunov function to show that $\mu$ is the unique global attractor for our algorithm's limiting dynamics, and (b) the use of martingale and stopping-time theory to show that our algorithm's iterates are almost surely bounded.

📄 PDF Abstract BibTeX arXiv:2304.01525

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups

2024-09-27 · Fengyu Gao, Ruiquan Huang, Jing Yang

We study the problems of differentially private federated online prediction from experts against both stochastic adversaries and oblivious adversaries. We aim to minimize the average regret on $m$ clients working in para…

Smoothed Analysis of Online and Differentially Private Learning

2020-06-17 · NeurIPS 2020 12 · Nika Haghtalab, Tim Roughgarden, Abhishek Shetty

Practical and pervasive needs for robustness and privacy in algorithms have inspired the design of online adversarial and differentially private learning algorithms. The primary quantity that characterizes learnability i…

Private Online Prediction from Experts: Separations and Faster Rates

2022-10-24 · Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar

Online prediction from experts is a fundamental problem in machine learning and several works have studied this problem under privacy constraints. We propose and analyze new algorithms for this problem that improve over …

The Limits of Differential Privacy in Online Learning

2024-11-08 · Bo Li, Wei Wang, Peng Ye

Differential privacy (DP) is a formal notion that restricts the privacy leakage of an algorithm when running on sensitive data, in which privacy-utility trade-off is one of the central problems in private data analysis. …

Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks

2022-01-28 · Bartłomiej Polaczyk, Jacek Cyranka

We study the overparametrization bounds required for the global convergence of stochastic gradient descent algorithm for a class of one hidden layer feed-forward neural networks, considering most of the activation functi…