**Click to Read Paper**

GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks

Jan 05, 2018

Alessandro Bay, Biswa Sengupta

Jan 05, 2018

Alessandro Bay, Biswa Sengupta

**Click to Read Paper**

Approximating meta-heuristics with homotopic recurrent neural networks

Sep 07, 2017

Alessandro Bay, Biswa Sengupta

Sep 07, 2017

Alessandro Bay, Biswa Sengupta

**Click to Read Paper**

Convolutional Recurrent Predictor: Implicit Representation for Multi-target Filtering and Tracking

Nov 01, 2018

Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez

Nov 01, 2018

Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez

**Click to Read Paper**

Deep Recurrent Neural Network for Multi-target Filtering

Oct 08, 2018

Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez

Oct 08, 2018

Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez

* The 25th International Conference on MultiMedia Modeling (MMM)

**Click to Read Paper**

Hide and Seek tracker: Real-time recovery from target loss

Jun 20, 2018

Alessandro Bay, Panagiotis Sidiropoulos, Eduard Vazquez, Michele Sasdelli

Jun 20, 2018

Alessandro Bay, Panagiotis Sidiropoulos, Eduard Vazquez, Michele Sasdelli

**Click to Read Paper**

Emergence of Invariance and Disentanglement in Deep Representations

Jun 28, 2018

Alessandro Achille, Stefano Soatto

Jun 28, 2018

Alessandro Achille, Stefano Soatto

* Deep learning, neural network, representation, flat minima, information bottleneck, overfitting, generalization, sufficiency, minimality, sensitivity, information complexity, stochastic gradient descent, regularization, total correlation, PAC-Bayes

**Click to Read Paper**

Credal Classification based on AODE and compression coefficients

Mar 27, 2012

Giorgio Corani, Alessandro Antonucci

Mar 27, 2012

Giorgio Corani, Alessandro Antonucci

**Click to Read Paper**

Reliable Uncertain Evidence Modeling in Bayesian Networks by Credal Networks

Feb 15, 2018

Sabina Marchetti, Alessandro Antonucci

Feb 15, 2018

Sabina Marchetti, Alessandro Antonucci

* 19 pages

**Click to Read Paper**

A Separation Principle for Control in the Age of Deep Learning

Nov 09, 2017

Alessandro Achille, Stefano Soatto

We review the problem of defining and inferring a "state" for a control system based on complex, high-dimensional, highly uncertain measurement streams such as videos. Such a state, or representation, should contain all and only the information needed for control, and discount nuisance variability in the data. It should also have finite complexity, ideally modulated depending on available resources. This representation is what we want to store in memory in lieu of the data, as it "separates" the control task from the measurement process. For the trivial case with no dynamics, a representation can be inferred by minimizing the Information Bottleneck Lagrangian in a function class realized by deep neural networks. The resulting representation has much higher dimension than the data, already in the millions, but it is smaller in the sense of information content, retaining only what is needed for the task. This process also yields representations that are invariant to nuisance factors and having maximally independent components. We extend these ideas to the dynamic case, where the representation is the posterior density of the task variable given the measurements up to the current time, which is in general much simpler than the prediction density maintained by the classical Bayesian filter. Again this can be finitely-parametrized using a deep neural network, and already some applications are beginning to emerge. No explicit assumption of Markovianity is needed; instead, complexity trades off approximation of an optimal representation, including the degree of Markovianity.
Nov 09, 2017

Alessandro Achille, Stefano Soatto

**Click to Read Paper**

A Bayesian Approach to Sparse plus Low rank Network Identification

Sep 26, 2015

Mattia Zorzi, Alessandro Chiuso

We consider the problem of modeling multivariate time series with parsimonious dynamical models which can be represented as sparse dynamic Bayesian networks with few latent nodes. This structure translates into a sparse plus low rank model. In this paper, we propose a Gaussian regression approach to identify such a model.
Sep 26, 2015

Mattia Zorzi, Alessandro Chiuso

**Click to Read Paper**

Identification of stable models via nonparametric prediction error methods

Jul 02, 2015

Diego Romeres, Gianluigi Pillonetto, Alessandro Chiuso

A new Bayesian approach to linear system identification has been proposed in a series of recent papers. The main idea is to frame linear system identification as predictor estimation in an infinite dimensional space, with the aid of regularization/Bayesian techniques. This approach guarantees the identification of stable predictors based on the prediction error minimization. Unluckily, the stability of the predictors does not guarantee the stability of the impulse response of the system. In this paper we propose and compare various techniques to address this issue. Simulations results comparing these techniques will be provided.
Jul 02, 2015

Diego Romeres, Gianluigi Pillonetto, Alessandro Chiuso

* number of pages = 6, number of figures = 3

**Click to Read Paper**

A scaled gradient projection method for Bayesian learning in dynamical systems

Feb 02, 2015

Silvia Bonettini, Alessandro Chiuso, Marco Prato

Feb 02, 2015

Silvia Bonettini, Alessandro Chiuso, Marco Prato

* SIAM Journal on Scientific Computing 37 (2015), A1297-A1318

**Click to Read Paper**

Bayesian and regularization approaches to multivariable linear system identification: the role of rank penalties

Sep 29, 2014

Giulia Prando, Alessandro Chiuso, Gianluigi Pillonetto

Sep 29, 2014

Giulia Prando, Alessandro Chiuso, Gianluigi Pillonetto

* to appear in IEEE Conference on Decision and Control, 2014

**Click to Read Paper**

A probabilistic network for the diagnosis of acute cardiopulmonary diseases

May 12, 2018

Alessandro Magrini, Davide Luciani, Federico Mattia Stefanini

In this paper, the development of a probabilistic network for the diagnosis of acute cardiopulmonary diseases is presented. This paper is a draft version of the article published after peer review in 2018 (https://doi.org/10.1002/bimj.201600206). A panel of expert physicians collaborated to specify the qualitative part, that is a directed acyclic graph defining a factorization of the joint probability distribution of domain variables. The quantitative part, that is the set of all conditional probability distributions defined by each factor, was estimated in the Bayesian paradigm: we applied a special formal representation, characterized by a low number of parameters and a parameterization intelligible for physicians, elicited the joint prior distribution of parameters from medical experts, and updated it by conditioning on a dataset of hospital patient records using Markov Chain Monte Carlo simulation. Refinement was cyclically performed until the probabilistic network provided satisfactory Concordance Index values for a selection of acute diseases and reasonable inference on six fictitious patient cases. The probabilistic network can be employed to perform medical diagnosis on a total of 63 diseases (38 acute and 25 chronic) on the basis of up to 167 patient findings.
May 12, 2018

Alessandro Magrini, Davide Luciani, Federico Mattia Stefanini

* Biometrical Journal, 60(1), 174-195, January 2018

* The DOI of the article published after peer review was added. A technical detail was added in Section 3.2, Formula 8 (as a consequence, the ID of all the subsequent formulas result augmented by 1 with respect to the previous version). The prior standard deviation of the Gamma distribution in Table 4 was fixed (in the previous version, the prior variance was indicated, instead)

**Click to Read Paper**

VFunc: a Deep Generative Model for Functions

Jul 11, 2018

Philip Bachman, Riashat Islam, Alessandro Sordoni, Zafarali Ahmed

Jul 11, 2018

Philip Bachman, Riashat Islam, Alessandro Sordoni, Zafarali Ahmed

* To be presented at the ICML 2018 workshop on Prediction and Generative Modeling in Reinforcement Learning

**Click to Read Paper**

On-line Bayesian System Identification

Jan 17, 2016

Diego Romeres, Giulia Prando, Gianluigi Pillonetto, Alessandro Chiuso

Jan 17, 2016

Diego Romeres, Giulia Prando, Gianluigi Pillonetto, Alessandro Chiuso

**Click to Read Paper**

Epistemic irrelevance in credal nets: the case of imprecise Markov trees

Aug 15, 2010

Gert de Cooman, Filip Hermans, Alessandro Antonucci, Marco Zaffalon

Aug 15, 2010

Gert de Cooman, Filip Hermans, Alessandro Antonucci, Marco Zaffalon

* 29 pages, 5 figures, 1 table

**Click to Read Paper**

Convex vs nonconvex approaches for sparse estimation: GLasso, Multiple Kernel Learning and Hyperparameter GLasso

Feb 27, 2013

Aleksandr Y. Aravkin, James V. Burke, Alessandro Chiuso, Gianluigi Pillonetto

The popular Lasso approach for sparse estimation can be derived via marginalization of a joint density associated with a particular stochastic model. A different marginalization of the same probabilistic model leads to a different non-convex estimator where hyperparameters are optimized. Extending these arguments to problems where groups of variables have to be estimated, we study a computational scheme for sparse estimation that differs from the Group Lasso. Although the underlying optimization problem defining this estimator is non-convex, an initialization strategy based on a univariate Bayesian forward selection scheme is presented. This also allows us to define an effective non-convex estimator where only one scalar variable is involved in the optimization process. Theoretical arguments, independent of the correctness of the priors entering the sparse model, are included to clarify the advantages of this non-convex technique in comparison with other convex estimators. Numerical experiments are also used to compare the performance of these approaches.
Feb 27, 2013

Aleksandr Y. Aravkin, James V. Burke, Alessandro Chiuso, Gianluigi Pillonetto

* 50 pages, 12 figures

**Click to Read Paper**

Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms

Oct 25, 2018

Andreea Anghel, Nikolaos Papandreou, Thomas Parnell, Alessandro De Palma, Haralampos Pozidis

Oct 25, 2018

Andreea Anghel, Nikolaos Papandreou, Thomas Parnell, Alessandro De Palma, Haralampos Pozidis

* 7 pages

**Click to Read Paper**