paper-with-me

Papers

A Mirror Descent-Based Algorithm for Corruption-Tolerant Distributed Gradient Descent

2024-07-19 · Shuche Wang, Vincent Y. F. Tan

Distributed gradient descent algorithms have come to the fore in modern machine learning, especially in parallelizing the handling of large datasets that are distributed across several workers. However, scant attention has been paid to analyzing the behavior of distributed gradient descent algorithms in the presence of adversarial corruptions instead of random noise. In this paper, we formulate a novel problem in which adversarial corruptions are present in a distributed learning system. We show how to use ideas from (lazy) mirror descent to design a corruption-tolerant distributed optimization algorithm. Extensive convergence analysis for (strongly) convex loss functions is provided for different choices of the stepsize. We carefully optimize the stepsize schedule to accelerate the convergence of the algorithm, while at the same time amortizing the effect of the corruption over time. Experiments based on linear regression, support vector classification, and softmax classification on the MNIST dataset corroborate our theoretical findings.

📄 PDF Abstract BibTeX arXiv:2407.14111

Code (0)

등록된 구현이 없습니다.

Tasks

Distributed Optimization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Distributed Mirror Descent with Integral Feedback: Asymptotic Convergence Analysis of Continuous-time Dynamics

2020-09-14 · Youbang Sun, Shahin Shahrampour

This work addresses distributed optimization, where a network of agents wants to minimize a global strongly convex objective function. The global function can be written as a sum of local convex functions, each of which …

Distributed Optimization

Privacy-Preserving Distributed Online Mirror Descent for Nonconvex Optimization

2025-01-08 · Yingjie Zhou, Tao Li

We investigate the distributed online nonconvex optimization problem with differential privacy over time-varying networks. Each node minimizes the sum of several nonconvex functions while preserving the node's differenti…

Privacy Preserving

Robust Imitation via Mirror Descent Inverse Reinforcement Learning

2022-10-20 · Dong-Sig Han, Hyunseo Kim, Hyundo Lee, Je-Hwan Ryu 외

Recently, adversarial imitation learning has shown a scalable reward acquisition method for inverse reinforcement learning (IRL) problems. However, estimated reward signals often become uncertain and fail to train a reli…

Density EstimationImitation Learningreinforcement-learningReinforcement Learning+1

Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise

2026-03-16 · Naoto Tani, Futoshi Futami arxiv

We study linear contextual bandits under adversarial corruption and heavy-tailed noise with finite $(1+ε)$-th moments for some $ε\in (0,1]$. Existing work that addresses both adversarial corruption and heavy-tailed noise…

Stochastic Optimization from Distributed, Streaming Data in Rate-limited Networks

2017-04-25 · Matthew Nokleby, Waheed U. Bajwa

Motivated by machine learning applications in networks of sensors, internet-of-things (IoT) devices, and autonomous agents, we propose techniques for distributed stochastic convex learning from high-rate data streams. Th…

Stochastic Optimization