arXiv subjects

Naoya Yoshida

Publications and source records attributed to Naoya Yoshida.

3 recordsLinked to original sources

arXiv2026

Semiclassical shape resonances for magnetic Stark Hamiltonians

We study shape resonances of two-dimensional magnetic Stark Hamiltonians in the semiclassical limit. The magnetic field is assumed to be constant and the scalar potential is a perturbation of a linear potential. Under the assumption that the scalar potential has potential wells, the existence of a one-to-one correspondence between shape resonances of the Hamiltonian and discrete eigenvalues of a certain reference operator is proved. This implies the Weyl law for the number of resonances and the asymptotic behavior of the real parts of resonances near the bottom of a potential well. Resonances are studied as complex eigenvalues of complex distorted Hamiltonians, which is defined by the complex translation outside a compact set.

math-ph↗

arXiv2020

MAB-based Client Selection for Federated Learning with Uncertain Resources in Mobile Networks

This paper proposes a client selection method for federated learning (FL) when the computation and communication resource of clients cannot be estimated; the method trains a machine learning (ML) model using the rich data and computational resources of mobile clients without collecting their data in central systems. Conventional FL with client selection estimates the required time for an FL round from a given clients' computation power and throughput and determines a client set to reduce time consumption in FL rounds. However, it is difficult to obtain accurate resource information for all clients before the FL process is conducted because the available computation and communication resources change easily based on background computation tasks, background traffic, bottleneck links, etc. Consequently, the FL operator must select clients through exploration and exploitation processes. This paper proposes a multi-armed bandit (MAB)-based client selection method to solve the exploration and exploitation trade-off and reduce the time consumption for FL in mobile networks. The proposed method balances the selection of clients for which the amount of resources is uncertain and those known to have a large amount of resources. The simulation evaluation demonstrated that the proposed scheme requires less learning time than the conventional method in the resource fluctuating scenario.

cs.NI↗

arXiv2020

Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data

This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients without gathering their data to central systems. The data of mobile clients is typically non-IID owing to diversity among mobile clients' interests and usage, and FL with non-IID data could degrade the model performance. Therefore, to mitigate the degradation induced by non-IID data, we assume that a limited number (e.g., less than 1%) of clients allow their data to be uploaded to a server, and we propose a hybrid learning mechanism referred to as Hybrid-FL, wherein the server updates the model using the data gathered from the clients and aggregates the model with the models trained by clients. The Hybrid-FL solves both client- and data-selection problems via heuristic algorithms, which try to select the optimal sets of clients who train models with their own data, clients who upload their data to the server, and data uploaded to the server. The algorithms increase the number of clients participating in FL and make more data gather in the server IID, thereby improving the prediction accuracy of the aggregated model. Evaluations, which consist of network simulations and ML experiments, demonstrate that the proposed scheme achieves a 13.5% higher classification accuracy than those of the previously proposed schemes for the non-IID case.

cs.LG↗