5 papers
Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning
Alireza Moayedikia, Alicia Troncoso Lora
Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone. A n…
Adaptive Temporal Gating of Longitudinal Magnetic Resonance Imaging for Alzheimer's Prediction
Alireza Moayedikia, Sara Fin, Alicia Troncoso Lora +1
Predicting conversion from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) is critical for early intervention. Current deep learning paradigms predominantly rely on cro…
Quantifying Gate Contribution in Quantum Feature Maps for Scalable Circuit Optimization
F. RodrÃguez-DÃaz, D. Gutiérrez-Avilés, A. Troncoso +1
Quantum machine learning offers promising advantages for classification tasks, but noise, decoherence, and connectivity constraints in current devices continue to limit the efficie…
Bridging Training and Merging Through Momentum-Aware Optimization
Alireza Moayedikia, Alicia Troncoso
Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued…
Learning based on neurovectors for tabular data: a new neural network approach
J. C. Husillos, A. Gallego, A. Roma +1
In this paper, we present a novel learning approach based on Neurovectors, an innovative paradigm that structures information through interconnected nodes and vector relationships…