Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Niu, Xiaochun"'
Collaborative learning enables multiple clients to learn shared feature representations across local data distributions, with the goal of improving model performance and reducing overall sample complexity. While empirical evidence shows the success o
Externí odkaz:
http://arxiv.org/abs/2409.04919
In this paper, we propose a family of label recovery problems on weighted Euclidean random graphs. The vertices of a graph are embedded in $\mathbb{R}^d$ according to a Poisson point process, and are assigned to a discrete community label. Our goal i
Externí odkaz:
http://arxiv.org/abs/2407.11163
We study the problem of exact community recovery in the Geometric Stochastic Block Model (GSBM), where each vertex has an unknown community label as well as a known position, generated according to a Poisson point process in $\mathbb{R}^d$. Edges are
Externí odkaz:
http://arxiv.org/abs/2307.11196
Generalization performance is a key metric in evaluating machine learning models when applied to real-world applications. Good generalization indicates the model can predict unseen data correctly when trained under a limited number of data. Federated
Externí odkaz:
http://arxiv.org/abs/2306.03824
Autor:
Niu, Xiaochun, Wei, Ermin
We study distributed optimization problems over multi-agent networks, including consensus and network flow problems. Existing distributed methods neglect the heterogeneity among agents' computational capabilities, limiting their effectiveness. To add
Externí odkaz:
http://arxiv.org/abs/2212.02638
Autor:
Niu, Xiaochun, Wei, Ermin
We consider solving distributed consensus optimization problems over multi-agent networks. Current distributed methods fail to capture the heterogeneity among agents' local computation capacities. We propose DISH as a distributed hybrid primal-dual a
Externí odkaz:
http://arxiv.org/abs/2206.03624
Autor:
Niu, Xiaochun, Wei, Ermin
We consider a multi-agent consensus optimization problem over a server-client (federated) network, where all clients are connected to a central server. Current distributed algorithms fail to capture the heterogeneity in clients' local computation cap
Externí odkaz:
http://arxiv.org/abs/2106.01279
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Niu, Xiaochun, Wei, Ermin
We study the minimax optimization problems that model many centralized and distributed computing applications. Existing works mainly focus on designing and analyzing specific methods, such as the gradient descent ascent method (GDA) and its variants
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78a85d3f2ec8112b5406c4d8254d5a59
http://arxiv.org/abs/2212.02638
http://arxiv.org/abs/2212.02638