Andrea Bragagnolo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Andrea Bragagnolo has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Enzo Tartaglione
Télécom Paris, Institut polytechnique de Paris
5 shared publications - Marco Grangetto
University of Turin
5 shared publications - Attilio Fiandrotti
University of Turin, Italy and LTCI, Télécom Paris, Institut polytechnique de Paris, France
3 shared publications - Gianluca Dalmasso
Università degli Studi di Torino Torino, Italy
2 shared publications - Riccardo Renzulli
University of Turin
2 shared publications - Carlo Alberto Barbano
University of Turin
1 shared publication
Latest Publications
- Open Access
- 26 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 696
Towards a validation-less approach for small data: training with neural velocity
- 26 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 696
Open AccessTowards a validation-less approach for small data: training with neural velocity
- 2 January 2026
- Published by Springer Nature
- p. 152-163
When Does Pruning Benefit Vision Representations?
- 2 January 2026
- Published by Springer Nature
- p. 152-163
When Does Pruning Benefit Vision Representations?
- Open Access
- 28 November 2025
- Published by Elsevier in Neurocomputing
- Vol. 668
TEP-ones: A simple yet effective approach for transferability estimation of pruned backbones
- 28 November 2025
- Published by Elsevier in Neurocomputing
- Vol. 668
Open AccessTEP-ones: A simple yet effective approach for transferability estimation of pruned backbones
- Open Access
Neural Velocity for hyperparameter tuning
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 approach that adjusts the learning rate and defines the stop criterion based on the novel notion of "neural velocity". The neural velocity measures the rate of change of each neuron's transfer function and is an indicator of model convergence: sampling neural velocity can be performed even by forwarding noise in the network, reducing the need for a held-out dataset. Our findings show the potential of neural velocity as a key metric for optimizing neural network training efficiently
Open AccessNeural Velocity for hyperparameter tuning
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 approach that adjusts the learning rate and defines the stop criterion based on the novel notion of "neural velocity". The neural velocity measures the rate of change of each neuron's transfer function and is an indicator of model convergence: sampling neural velocity can be performed even by forwarding noise in the network, reducing the need for a held-out dataset. Our findings show the potential of neural velocity as a key metric for optimizing neural network training efficiently
- Open Access
To update or not to update? Neurons at equilibrium in deep models
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 training a subset of their parameters. Such a discovery has a broad impact from theory to applications, driving the research towards methods to identify the minimum subset of parameters to train without look-ahead information exploitation. However, the methods proposed do not match the state-of-the-art performance, and rely on unstructured sparsely connected models. In this work we shift our focus from the single parameters to the behavior of the whole neuron, exploiting the concept of neuronal equilibrium (NEq). When a neuron is in a configuration at equilibrium (meaning that it has learned a specific input-output relationship), we can halt its update; on the contrary, when a neuron is at non-equilibrium, we let its state evolve towards an equilibrium state, updating its parameters. The proposed approach has been tested on different state-of-the-art learning strategies and tasks, validating NEq and observing that the neuronal equilibrium depends on the specific learning setup.
Open AccessTo update or not to update? Neurons at equilibrium in deep models
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 training a subset of their parameters. Such a discovery has a broad impact from theory to applications, driving the research towards methods to identify the minimum subset of parameters to train without look-ahead information exploitation. However, the methods proposed do not match the state-of-the-art performance, and rely on unstructured sparsely connected models. In this work we shift our focus from the single parameters to the behavior of the whole neuron, exploiting the concept of neuronal equilibrium (NEq). When a neuron is in a configuration at equilibrium (meaning that it has learned a specific input-output relationship), we can halt its update; on the contrary, when a neuron is at non-equilibrium, we let its state evolve towards an equilibrium state, updating its parameters. The proposed approach has been tested on different state-of-the-art learning strategies and tasks, validating NEq and observing that the neuronal equilibrium depends on the specific learning setup.
- Open Access
Pruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima
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 loss. However, there is a general lack in understanding why these pruning strategies are effective. In this work, we are going to compare and analyze pruned solutions with two different pruning approaches, one-shot and gradual, showing the higher effectiveness of the latter. In particular, we find that gradual pruning allows access to narrow, well-generalizing minima, which are typically ignored when using one-shot approaches. In this work we also propose PSP-entropy, a measure to understand how a given neuron correlates to some specific learned classes. Interestingly, we observe that the features extracted by iteratively-pruned models are less correlated to specific classes, potentially making these models a better fit in transfer learning approaches.
Open AccessPruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima
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 loss. However, there is a general lack in understanding why these pruning strategies are effective. In this work, we are going to compare and analyze pruned solutions with two different pruning approaches, one-shot and gradual, showing the higher effectiveness of the latter. In particular, we find that gradual pruning allows access to narrow, well-generalizing minima, which are typically ignored when using one-shot approaches. In this work we also propose PSP-entropy, a measure to understand how a given neuron correlates to some specific learned classes. Interestingly, we observe that the features extracted by iteratively-pruned models are less correlated to specific classes, potentially making these models a better fit in transfer learning approaches.