30 citations · 61 across the 8 of their papers we have counts for
5 papers · 1 filter
Neural Velocity for hyperparameter tuning
Gianluca Dalmasso, Andrea Bragagnolo, Enzo Tartaglione +2
Hyperparameter tuning, such as learning rate decay and defining a stopping criterion, often relies on monitoring the validation loss. This paper presents NeVe, a dynamic training a…
To update or not to update? Neurons at equilibrium in deep models
Andrea Bragagnolo, Enzo Tartaglione, Marco Grangetto
Recent advances in deep learning optimization showed that, with some a-posteriori information on fully-trained models, it is possible to match the same performance by simply traini…
SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networks
Enzo Tartaglione, Andrea Bragagnolo, Francesco Odierna +2
Deep neural networks include millions of learnable parameters, making their deployment over resource-constrained devices problematic. SeReNe (Sensitivity-based Regularization of Ne…
LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networks
Enzo Tartaglione, Andrea Bragagnolo, Attilio Fiandrotti +1
LOBSTER (LOss-Based SensiTivity rEgulaRization) is a method for training neural networks having a sparse topology. Let the sensitivity of a network parameter be the variation of th…
Pruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima
Enzo Tartaglione, Andrea Bragagnolo, Marco Grangetto
Recently, a race towards the simplification of deep networks has begun, showing that it is effectively possible to reduce the size of these models with minimal or no performance lo…