Elena Agliari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Elena Agliari has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Adriano Barra
Sapienza Università di Roma
17 shared publications - Alberto Fachechi
Dipartimento di Matematica, “Guido Castelnuovo”, Sapienza Università di Roma, Roma, Italy
14 shared publications - Francesco Alemanno
Dipartimento di Matematica e Fisica E. De Giorgi Università del Salento I-73100 Lecce Italy
10 shared publications Adriano Barra
Ist Nazl Alta Matemat, GNFM INdAM, Grp Nazl Fis Matemat, Rome, Italy
6 shared publicationsAlberto Fachechi
5 shared publicationsMiriam Aquaro
Dipartimento di Matematica, Sapienza University of Roma, P. le A. Moro 5, 00185 Roma, Italy
5 shared publications
Latest Publications
- Open Access
- 28 July 2026
- Published by Springer Nature in Bollettino dell'Unione Matematica Italiana
- p. 1-31
Pattern disentanglement and reconstruction by modular Hebbian networks
We address the problem of reconstructing a set of K binary patterns $$\varvec{\Xi }= (\varvec{\xi }^1,..., \varvec{\xi }^K) \in \{-1, +1 \}^{N \times K}$$ , starting from their covariance matrix $$\varvec{\Xi }\varvec{\Xi }^T$$ and from a set of mixtures of the form $$\varvec{\sigma }_M= \text {sign}(\sum _{\mu \in \mathcal {S}_M \subseteq \{1,..., K\}} \varvec{\xi }^{\mu })$$ , with $$\left\lvert S_M\right\rvert =M$$ . To this aim, we engage a modular Hebbian network, specified by the interaction matrix $$\varvec{J}^H = \frac{1}{N}\varvec{\Xi }\varvec{\Xi }^T$$ , where $${\varvec{\sigma }_M}$$ is taken as the initial state, repeated in each of the constituting L modules and the stable state resulting from a Gibbs evolution rule is taken as an L -tuple of candidate patterns. Finally, by properly handling $$\varvec{J}^H$$ we can derive the projector matrix $$\varvec{J}^K = \varvec{\Xi }(\varvec{\Xi }^T \varvec{\Xi })^{-1} \varvec{\Xi }^T$$ by which we can determine whether these candidate patterns are a good estimate for the ground patterns.- 28 July 2026
- Published by Springer Nature in Bollettino dell'Unione Matematica Italiana
- p. 1-31
Open AccessPattern disentanglement and reconstruction by modular Hebbian networks
We address the problem of reconstructing a set of K binary patterns $$\varvec{\Xi }= (\varvec{\xi }^1,..., \varvec{\xi }^K) \in \{-1, +1 \}^{N \times K}$$ , starting from their covariance matrix $$\varvec{\Xi }\varvec{\Xi }^T$$ and from a set of mixtures of the form $$\varvec{\sigma }_M= \text {sign}(\sum _{\mu \in \mathcal {S}_M \subseteq \{1,..., K\}} \varvec{\xi }^{\mu })$$ , with $$\left\lvert S_M\right\rvert =M$$ . To this aim, we engage a modular Hebbian network, specified by the interaction matrix $$\varvec{J}^H = \frac{1}{N}\varvec{\Xi }\varvec{\Xi }^T$$ , where $${\varvec{\sigma }_M}$$ is taken as the initial state, repeated in each of the constituting L modules and the stable state resulting from a Gibbs evolution rule is taken as an L -tuple of candidate patterns. Finally, by properly handling $$\varvec{J}^H$$ we can derive the projector matrix $$\varvec{J}^K = \varvec{\Xi }(\varvec{\Xi }^T \varvec{\Xi })^{-1} \varvec{\Xi }^T$$ by which we can determine whether these candidate patterns are a good estimate for the ground patterns. - Open Access
- 6 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 694
The importance of being empty: Hopfield neural networks with diluted examples
- 6 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 694
Open AccessThe importance of being empty: Hopfield neural networks with diluted examples
- Open Access
- 15 November 2025
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 682
The beneficial role of noises for disentanglement tasks in modular Hebbian networks
- 15 November 2025
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 682
Open AccessThe beneficial role of noises for disentanglement tasks in modular Hebbian networks
- Open Access
- 9 October 2025
- Published by Elsevier in Neural Networks
- Vol. 194, 108181
Networks of Hebbian networks: more is different
- 9 October 2025
- Published by Elsevier in Neural Networks
- Vol. 194, 108181
Open AccessNetworks of Hebbian networks: more is different
- Open Access
- 10 February 2025
- Published by IOP Publishing in Journal of Physics A: Mathematical and Theoretical
- Vol. 58 (6) , 065004
Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines
We consider restricted Boltzmann machines with a binary visible layer and a Gaussian hidden layer trained by an unlabelled dataset composed of noisy realizations of a single ground pattern. We develop a statistical mechanics framework to describe the network generative capabilities, by exploiting the replica trick and assuming self-averaging of the underlying order parameters (i.e. replica symmetry). In particular, we outline the effective control parameters (e.g. the relative number of weights to be trained, the regularization parameter), whose tuning can yield qualitatively-different operative regimes. Further, we provide analytical and numerical evidence for the existence of a sub-region in the space of the hyperparameters where replica-symmetry breaking occurs.
- 10 February 2025
- Published by IOP Publishing in Journal of Physics A: Mathematical and Theoretical
- Vol. 58 (6) , 065004
Open AccessFundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines
We consider restricted Boltzmann machines with a binary visible layer and a Gaussian hidden layer trained by an unlabelled dataset composed of noisy realizations of a single ground pattern. We develop a statistical mechanics framework to describe the network generative capabilities, by exploiting the replica trick and assuming self-averaging of the underlying order parameters (i.e. replica symmetry). In particular, we outline the effective control parameters (e.g. the relative number of weights to be trained, the regularization parameter), whose tuning can yield qualitatively-different operative regimes. Further, we provide analytical and numerical evidence for the existence of a sub-region in the space of the hyperparameters where replica-symmetry breaking occurs.
- Open Access
- 13 January 2025
- Published by IOP Publishing in Journal of Physics A: Mathematical and Theoretical
Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines
We consider restricted Boltzmann machines with a binary visible layer and a Gaussian hidden layer trained by an unlabelled dataset composed of noisy realizations of a single ground pattern. We develop a statistical mechanics framework to describe the network generative capabilities, by exploiting the replica trick and assuming self-averaging of the underlying order parameters (i.e., replica symmetry). In particular, we outline the effective control parameters (e.g., the relative number of weights to be trained, the regularization parameter), whose tuning can yield qualitatively-different operative regimes. Further, we provide analytical and numerical evidence for the existence of a sub-region in the space of the hyperparameters where replica-symmetry breaking occurs.
- 13 January 2025
- Published by IOP Publishing in Journal of Physics A: Mathematical and Theoretical
Open AccessFundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines
We consider restricted Boltzmann machines with a binary visible layer and a Gaussian hidden layer trained by an unlabelled dataset composed of noisy realizations of a single ground pattern. We develop a statistical mechanics framework to describe the network generative capabilities, by exploiting the replica trick and assuming self-averaging of the underlying order parameters (i.e., replica symmetry). In particular, we outline the effective control parameters (e.g., the relative number of weights to be trained, the regularization parameter), whose tuning can yield qualitatively-different operative regimes. Further, we provide analytical and numerical evidence for the existence of a sub-region in the space of the hyperparameters where replica-symmetry breaking occurs.
- 1 August 2024
- Published by American Physical Society (APS) in Physical Review E
- Vol. 110 (2) , 024301
Inverse modeling of time-delayed interactions via the dynamic-entropy formalism
Although instantaneous interactions are unphysical, a large variety of maximum entropy statistical inference methods match the model-inferred and the empirically measured equal-time correlation functions. Focusing on collective motion of active units, this constraint is reasonable when the interaction timescale is much faster than that of the interacting units, as in starling flocks, yet it fails in a number of counterexamples, as in leukocyte coordination (where signaling proteins diffuse among two cells). Here, we relax this assumption and develop a path integral approach to maximum-entropy framework, which includes delay in signaling. Our method is able to infer the strength of couplings and fields, but also the time required by the couplings to completely transfer information among the units. We demonstrate the validity of our approach providing excellent results on synthetic datasets of non-Markovian trajectories generated by the Heisenberg-Kuramoto and Vicsek models equipped with delayed interactions. As a proof of concept, we also apply the method to experiments on dendritic migration, where matching equal-time correlations results in a significant information loss.
- 1 August 2024
- Published by American Physical Society (APS) in Physical Review E
- Vol. 110 (2) , 024301
Inverse modeling of time-delayed interactions via the dynamic-entropy formalism
Although instantaneous interactions are unphysical, a large variety of maximum entropy statistical inference methods match the model-inferred and the empirically measured equal-time correlation functions. Focusing on collective motion of active units, this constraint is reasonable when the interaction timescale is much faster than that of the interacting units, as in starling flocks, yet it fails in a number of counterexamples, as in leukocyte coordination (where signaling proteins diffuse among two cells). Here, we relax this assumption and develop a path integral approach to maximum-entropy framework, which includes delay in signaling. Our method is able to infer the strength of couplings and fields, but also the time required by the couplings to completely transfer information among the units. We demonstrate the validity of our approach providing excellent results on synthetic datasets of non-Markovian trajectories generated by the Heisenberg-Kuramoto and Vicsek models equipped with delayed interactions. As a proof of concept, we also apply the method to experiments on dendritic migration, where matching equal-time correlations results in a significant information loss.
- Top Cited PapersOpen Access
- 15 May 2024
- Published by Elsevier in Neural Networks
- Vol. 177, 106389
Regularization, early-stopping and dreaming: A Hopfield-like setup to address generalization and overfitting
- 15 May 2024
- Published by Elsevier in Neural Networks
- Vol. 177, 106389
Top Cited PapersOpen AccessRegularization, early-stopping and dreaming: A Hopfield-like setup to address generalization and overfitting
- Open Access
- 27 March 2024
- Published by Elsevier in Applied Mathematics and Computation
- Vol. 474
A spectral approach to Hebbian-like neural networks
- 27 March 2024
- Published by Elsevier in Applied Mathematics and Computation
- Vol. 474
Open AccessA spectral approach to Hebbian-like neural networks
- Open Access
Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting
In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal neuron-interaction matrices turn out to be a class of matrices which correspond to Hebbian kernels revised by a reiterated unlearning protocol. Remarkably, the extent of such unlearning is proved to be related to the regularization hyperparameter of the loss function and to the training time. Thus, we can design strategies to avoid overfitting that are formulated in terms of regularization and early-stopping tuning. The generalization capabilities of these attractor networks are also investigated: analytical results are obtained for random synthetic datasets, next, the emerging picture is corroborated by numerical experiments that highlight the existence of several regimes (i.e., overfitting, failure and success) as the dataset parameters are varied.
Open AccessRegularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting
In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal neuron-interaction matrices turn out to be a class of matrices which correspond to Hebbian kernels revised by a reiterated unlearning protocol. Remarkably, the extent of such unlearning is proved to be related to the regularization hyperparameter of the loss function and to the training time. Thus, we can design strategies to avoid overfitting that are formulated in terms of regularization and early-stopping tuning. The generalization capabilities of these attractor networks are also investigated: analytical results are obtained for random synthetic datasets, next, the emerging picture is corroborated by numerical experiments that highlight the existence of several regimes (i.e., overfitting, failure and success) as the dataset parameters are varied.