Zobrazeno 1 - 10
of 25 214
pro vyhledávání: '"Duong, P."'
We investigate the problem of agent-to-agent interaction in decentralized (federated) learning over time-varying directed graphs, and, in doing so, propose a consensus-based algorithm called DSGTm-TV. The proposed algorithm incorporates gradient trac
Externí odkaz:
http://arxiv.org/abs/2409.17189
In this paper, approximate optimality conditions and sensitivity analysis in nearly convex optimization are discussed. More precisely, as in the spirit of convex analysis, we introduce the concept of $\varepsilon$-subdifferential for nearly convex fu
Externí odkaz:
http://arxiv.org/abs/2410.04710
We deal with the task of sampling from an unnormalized Boltzmann density $\rho_D$ by learning a Boltzmann curve given by energies $f_t$ starting in a simple density $\rho_Z$. First, we examine conditions under which Fisher-Rao flows are absolutely co
Externí odkaz:
http://arxiv.org/abs/2410.03282
Autor:
Nguyen, Manh Duong, Nguyen, Trung Thanh, Pham, Huy Hieu, Hoang, Trong Nghia, Nguyen, Phi Le, Huynh, Thanh Trung
Federated Learning (FL) is a method for training machine learning models using distributed data sources. It ensures privacy by allowing clients to collaboratively learn a shared global model while storing their data locally. However, a significant ch
Externí odkaz:
http://arxiv.org/abs/2410.03070
Autor:
Nguyen, Minh Hieu, Nguyen, Huu Tien, Nguyen, Trung Thanh, Nguyen, Manh Duong, Hoang, Trong Nghia, Nguyen, Truong Thao, Nguyen, Phi Le
Federated Learning (FL) has emerged as a powerful paradigm for training machine learning models in a decentralized manner, preserving data privacy by keeping local data on clients. However, evaluating the robustness of these models against data pertu
Externí odkaz:
http://arxiv.org/abs/2410.03067
Autor:
Nguyen, Minh Duong, Le, Khanh, Do, Khoi, Tran, Nguyen H., Nguyen, Duc, Trinh, Chien, Yang, Zhaohui
In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergence, especially when gradients from different users form an obtuse angle
Externí odkaz:
http://arxiv.org/abs/2410.02845
Autor:
Lee, Joseph, Yang, Shu, Baik, Jae Young, Liu, Xiaoxi, Tan, Zhen, Li, Dawei, Wen, Zixuan, Hou, Bojian, Duong-Tran, Duy, Chen, Tianlong, Shen, Li
Predicting phenotypes with complex genetic bases based on a small, interpretable set of variant features remains a challenging task. Conventionally, data-driven approaches are utilized for this task, yet the high dimensional nature of genotype data m
Externí odkaz:
http://arxiv.org/abs/2410.01795
Autor:
Duong, Manh Khoi, Conrad, Stefan
The reason behind the unfair outcomes of AI is often rooted in biased datasets. Therefore, this work presents a framework for addressing fairness by debiasing datasets containing a (non-)binary protected attribute. The framework proposes a combinator
Externí odkaz:
http://arxiv.org/abs/2410.00836
Autor:
Duong, Ngoc My Hanh, Berhane, Amanuel M., Mitchell, Dave, Ullah, Rifat, Zhang, Ting, Zhu, He, Du, Jia, Lam, Simon K. H., Mitchell, Emma E., Bendavid, Avi
In this letter, we demonstrate for the first time the creation of Josephson-like superconducting nanojunctions using a thermal scanning probe to directly inscribe weak links into microstrips of YBa2Cu3O7-x (YBCO). Our method effectively reduces the c
Externí odkaz:
http://arxiv.org/abs/2410.00372
We consider the ordinary or fractional Laplacian plus a homogeneous, scaling-critical drift term. This operator is non-symmetric but homogeneous, and generates scales of $L^p$-Sobolev spaces which we compare with the ordinary homogeneous Sobolev spac
Externí odkaz:
http://arxiv.org/abs/2410.00191