Results 111 to 120 of about 7,049,980 (289)

Improving the Model Robustness of DFL in Non-IID Environment [PDF]

Federated Learning (FL) is vulnerable to poisoning attacks. While some defense mechanisms have been proposed, they predominantly assume IID date, which is usually not the case in real-world scenarios.
Zeng, Zien
core   +1 more source

Copula‐based joint modelling of emergency department visits with time‐varying dependence

Canadian Journal of Statistics, EarlyView.
Abstract Jointly modelling multiple correlated count time series is essential in health services research, where outcomes like emergency visits for mental health and substance use often evolve together. Ignoring these dependencies can obscure meaningful trends and limit the effectiveness of policy evaluation.
Guanjie Lyu, Cindy Feng, Lihui Liu
wiley   +1 more source

Non-iid hypothesis testing: from classical to quantum

CoRR
We study hypothesis testing (aka state certification) in the non-identically distributed setting. A recent work (Garg et al. 2023) considered the classical case, in which one is given (independent) samples from $T$ unknown probability distributions $p_1, \dots, p_T$ on $[d] = \{1, 2, \dots, d\}$, and one wishes to accept/reject the hypothesis that ...
Giacomo De Palma, Marco Fanizza, Connor Mowry, Ryan O'Donnell   +3 more
openaire   +2 more sources

Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA

Communications on Pure and Applied Mathematics, EarlyView.
ABSTRACT We study the high‐dimensional dynamics of online stochastic gradient descent (SGD) for the multi‐spiked tensor model. This multi‐index model arises from the tensor principal component analysis (PCA) problem with multiple spikes, where the goal is to estimate the unknown signal vectors within the N$N$‐dimensional unit sphere through maximum ...
Gérard Ben Arous, Cédric Gerbelot, Vanessa Piccolo   +2 more
wiley   +1 more source

VINO_EffiFedAV: VINO with efficient federated learning through selective client updates for real-time autonomous vehicle object detection

Results in Engineering
The advancement of autonomous vehicle technology relies heavily on sophisticated machine-learning models that facilitate real-time object detection and classification.
K. Vinoth, P. Sasikumar
doaj   +1 more source

Fintech Policy and the Rise of Green Technological Inventions

Corporate Social Responsibility and Environmental Management, EarlyView.
ABSTRACT Technological transformation can enhance enterprises' green invention by promoting knowledge spillovers, alleviating financial constraints, and supporting innovative business models. Within this framework, our study investigates the effect of technological infrastructure construction on green technology invention, using the ‘Fintech China ...
Tao Huang, Qurat ul Ain, Tahir Yousaf, Kaiyang Zhong   +3 more
wiley   +1 more source

2D Implementation of Kinetic‐Diffusion Monte Carlo in Eiron

Contributions to Plasma Physics, EarlyView.
ABSTRACT Particle‐based kinetic Monte Carlo simulations of neutral particles are one of the major computational bottlenecks in tokamak scrape‐off layer simulations. This computational cost comes from the need to resolve individual collision events in high‐collisional regimes.
Oskar Lappi, Emil Løvbak, Thijs Steel, Giovanni Samaey   +3 more
wiley   +1 more source

Seismic Structural Reliability by Time‐Variant Fragility Functions

Earthquake Engineering &Structural Dynamics, EarlyView.
ABSTRACT The seismic vulnerability of aging structures is often represented in the form of fragility curves that vary with time. On one hand, each of these functions is intended to apply if the earthquake hits at the time the fragility refers to. On the other hand, performance‐based earthquake engineering (PBEE) resources to classical probabilistic ...
Iunio Iervolino
wiley   +1 more source

Decentralized Federated Learning for Wind Turbine Bearing Prognostics Under Data Scarcity and Statistical Heterogeneity

Energy Science &Engineering, EarlyView.
This paper proposes a decentralized peer‐to‐peer federated learning framework for wind turbine bearing remaining useful life prediction, introducing a virtual client paradigm in which statistical health indicators serve as independent feature‐level clients—enabling privacy‐preserving collaborative prognostics from a single physical asset under ...
Jihene Sidhom, Lotfi Saidi, Eric Bechhoefer   +2 more
wiley   +1 more source

Cross-Domain Federated Data Modeling on Non-IID Data. [PDF]

Comput Intell Neurosci, 2022
Chai B, Liu K, Yang R.
europepmc   +1 more source