Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Combining Relevance and Magnitude for Resource-Aware DNN Pruning
Carla Fabiana Chiasserini, Francesco Malandrino, Nuria Molner +1
Pruning neural networks, i.e., removing some of their parameters whilst retaining their accuracy, is one of the main ways to reduce the latency of a machine learning pipeline, espe…
cs.LG2024
Edge-device Collaborative Computing for Multi-view Classification
Marco Palena, Tania Cerquitelli, Carla Fabiana Chiasserini
Motivated by the proliferation of Internet-of-Thing (IoT) devices and the rapid advances in the field of deep learning, there is a growing interest in pushing deep learning computa…
cs.LG2024
Dependable Distributed Training of Compressed Machine Learning Models
Francesco Malandrino, Giuseppe Di Giacomo, Marco Levorato +1
The existing work on the distributed training of machine learning (ML) models has consistently overlooked the distribution of the achieved learning quality, focusing instead on its…