3 papers
cs.LG2026
AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning
Ioannis Tsingalis, Constantine Kotropoulos, Corentin Briat
A novel regularization technique, AdaCubic, is proposed that adapts the weight of the cubic term. The heart of AdaCubic is an auxiliary optimization problem with cubic constraints…
cs.LG2025
Quantized Rank Reduction: A Communications-Efficient Federated Learning Scheme for Network-Critical Applications
Dimitrios Kritsiolis, Constantine Kotropoulos
Federated learning is a machine learning approach that enables multiple devices (i.e., agents) to train a shared model cooperatively without exchanging raw data. This technique kee…
cs.SD2025
InterGridNet: An Electric Network Frequency Approach for Audio Source Location Classification Using Convolutional Neural Networks
Christos Korgialas, Ioannis Tsingalis, Georgios Tzolopoulos +1
A novel framework, called InterGridNet, is introduced, leveraging a shallow RawNet model for geolocation classification of Electric Network Frequency (ENF) signatures in the SP Cup…