2 papers
cs.LG2025
Growth strategies for arbitrary DAG neural architectures
Stella Douka, Manon Verbockhaven, Théo Rudkiewicz +4
Deep learning has shown impressive results obtained at the cost of training huge neural networks. However, the larger the architecture, the higher the computational, financial, and…
cs.AI2024
Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally
Manon Verbockhaven, Sylvain Chevallier, Guillaume Charpiat +1
Machine learning tasks are generally formulated as optimization problems, where one searches for an optimal function within a certain functional space. In practice, parameterized f…