3 papers
cs.LG2026
Beyond a Single Explanation of the Adam--SGD Gap
Chenxiang Zhang, Rustem Islamov, Enea Monzio Compagnoni +3
Prior work has identified several factors that can contribute to the performance gap between Adam and SGD, spanning data aspects, architecture design, and optimization properties.…
q-bio.QM2025
Efficient Data Selection for Training Genomic Perturbation Models
George Panagopoulos, Johannes F. Lutzeyer, Sofiane Ennadir +2
Genomic studies face a vast hypothesis space, while interventions such as gene perturbations remain costly and time-consuming. To accelerate such experiments, gene perturbation mod…
cs.LG2025
KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning
Roman Bresson, Giannis Nikolentzos, George Panagopoulos +3
In recent years, Graph Neural Networks (GNNs) have become the de facto tool for learning node and graph representations. Most GNNs typically consist of a sequence of neighborhood a…