7 papers
SEAL: Searching Expandable Architectures for Incremental Learning
Matteo Gambella, Manuel Roveri
Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new t…
HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search
Matteo Gambella, Fabrizio Pittorino, Manuel Roveri
Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transit…
Architecture-Aware Minimization (AM): How to Find Flat Minima in Neural Architecture Search
Matteo Gambella, Fabrizio Pittorino, Manuel Roveri
Neural Architecture Search (NAS) has become an essential tool for designing effective and efficient neural networks. In this paper, we investigate the geometric properties of neura…
SQUAD: Scalable Quorum Adaptive Decisions via ensemble of early exit neural networks
Matteo Gambella, Fabrizio Pittorino, Giuliano Casale +1
Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approac…
NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks
Matteo Gambella, Jary Pomponi, Simone Scardapane +1
Early Exit Neural Networks (EENNs) endow astandard Deep Neural Network (DNN) with Early Exit Classifiers (EECs), to provide predictions at intermediate points of the processing whe…
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures
Miguel Nogales, Matteo Gambella, Manuel Roveri
Early exits (EEs) offer a promising approach to reducing computational costs and latency by dynamically terminating inference once a satisfactory prediction confidence on a data sa…