Výsledky vyhledávání

Report

Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation

Autor: Yang, Haibo, Qiu, Peiwen, Khanduri, Prashant, Fang, Minghong, Liu, Jia

Existing works in federated learning (FL) often assume an ideal system with either full client or uniformly distributed client participation. However, in practice, it has been observed that some clients may never participate in FL training (aka incom

Externí odkaz: http://arxiv.org/abs/2405.02745

Zobrazit plný text záznamu

Dissertation/ Thesis

Nursing interventions for patients with stroke : A descriptive review

Autor: Chen, Jing, Qiu, Peiwen

Background: Stroke is a global health problem, which affects more than 15 millionpeople each year worldwide and leads to high mortality and disability rates. Theprevalence and incidence of stroke in an aging population continued to rise, and somescho

Externí odkaz: http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-41822

Zobrazit plný text záznamu

Report

DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization

Autor: Qiu, Peiwen, Li, Yining, Liu, Zhuqing, Khanduri, Prashant, Liu, Jia, Shroff, Ness B., Bentley, Elizabeth Serena, Turck, Kurt

Decentralized bilevel optimization has received increasing attention recently due to its foundational role in many emerging multi-agent learning paradigms (e.g., multi-agent meta-learning and multi-agent reinforcement learning) over peer-to-peer edge

Externí odkaz: http://arxiv.org/abs/2212.02376

Zobrazit plný text záznamu

Report

Taming Fat-Tailed ('Heavier-Tailed' with Potentially Infinite Variance) Noise in Federated Learning

Autor: Yang, Haibo, Qiu, Peiwen, Liu, Jia

A key assumption in most existing works on FL algorithms' convergence analysis is that the noise in stochastic first-order information has a finite variance. Although this assumption covers all light-tailed (i.e., sub-exponential) and some heavy-tail

Externí odkaz: http://arxiv.org/abs/2210.00690

Zobrazit plný text záznamu

Report

CHARLES: Channel-Quality-Adaptive Over-the-Air Federated Learning over Wireless Networks

Autor: Mao, Jiayu, Yang, Haibo, Qiu, Peiwen, Liu, Jia, Yener, Aylin

Over-the-air federated learning (OTA-FL) has emerged as an efficient mechanism that exploits the superposition property of the wireless medium and performs model aggregation for federated learning in the air. OTA-FL is naturally sensitive to wireless

Externí odkaz: http://arxiv.org/abs/2205.09330

Zobrazit plný text záznamu

Report

Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control

Autor: Yang, Haibo, Qiu, Peiwen, Liu, Jia, Yener, Aylin

This paper considers over-the-air federated learning (OTA-FL). OTA-FL exploits the superposition property of the wireless medium, and performs model aggregation over the air for free. Thus, it can greatly reduce the communication cost incurred in com

Externí odkaz: http://arxiv.org/abs/2205.05867

Zobrazit plný text záznamu

Dissertation/ Thesis

Variability in the Pinna Motions of Hipposiderid Bats, Hipposideros Pratti

Autor: Qiu, Peiwen

Bats are known for their highly capable biosonar systems which make them be able to navigate and forage in dense vegetation. Their biosonar system consists of one emitter (nose or mouth) and two receivers (ears). Some bat species, e.g. in the rhinolo

Externí odkaz: http://hdl.handle.net/10919/96483

Zobrazit plný text záznamu