Search results for: Marcello Sanguineti

Items from 1 to 20 out of 51 results

article

Braess' paradox: A cooperative game‐theoretic point of view

Mauro Passacantando, Giorgio Gnecco, Yuval Hadas, Marcello Sanguineti

Networks > 78 > 3 > 264 - 283

Braess' paradox is a classical result in the theory of congestion games. It motivates theoretically why adding a resource (e.g., an arc) to a network may sometimes worsen, rather than improve, the overall network performance. Differently from previous literature, which studies Braess' paradox in a non‐cooperative game‐theoretic setting, in this work, a framework is proposed to investigate its occurrence...

article

Some properties of transportation network cooperative games

Giorgio Gnecco, Yuval Hadas, Marcello Sanguineti

Networks > 74 > 2 > 161 - 173

A basic question in network analysis concerns the quantification of the importance of each node in terms of network connectivity. To this end, a possible approach consists in using cooperative game theory tools to define a measure of node centrality. In this paper, given a transportation network, a cooperative game model with transferable utility (TU game) is considered. The nodes of the network represent...

article

Neural approximations in discounted infinite-horizon stochastic optimal control problems

Giorgio Gnecco, Marcello Sanguineti

Engineering Applications of Artificial Intelligence > 2018 > 74 > C > 294-302

Neural approximations of the optimal stationary closed-loop control strategies for discounted infinite-horizon stochastic optimal control problems are investigated. It is shown that for a family of such problems, the minimal number of network parameters needed to achieve a desired accuracy of the approximate solution does not grow exponentially with the number of state variables. In such a way, neural-network...

article

An approach to transportation network analysis via transferable utility games

Yuval Hadas, Giorgio Gnecco, Marcello Sanguineti

Transportation Research Part B: Methodological > 2017 > 105 > C > 120-143

Network connectivity is an important aspect of any transportation network, as the role of the network is to provide a society with the ability to easily travel from point to point using various modes. A basic question in network analysis concerns how “important” each node is. An important node might, for example, greatly contribute to short connections between many pairs of nodes, handle a large amount...

article

Commitment-Based Equilibrium Environmental Strategies Under Time-Dependent Absorption Efficiency

Fouad El Ouardighi, Konstantin Kogan, Giorgio Gnecco, Marcello Sanguineti

Group Decision and Negotiation > 2018 > 27 > 2 > 235-249

This paper investigates how current and future generations are affected by commitment-based Nash equilibrium environmental strategies when the environmental absorption efficiency is susceptible to switch from a pollution sink to a source. We formulate a two-player differential game model of transboundary pollution that includes the environmental absorption efficiency as a state variable that can be...

article

Probabilistic lower bounds for approximation by shallow perceptron networks

Věra Kůrková, Marcello Sanguineti

Neural Networks > 2017 > 91 > C > 34-41

Limitations of approximation capabilities of shallow perceptron networks are investigated. Lower bounds on approximation errors are derived for binary-valued functions on finite domains. It is proven that unless the number of network units is sufficiently large (larger than any polynomial of the logarithm of the size of the domain) a good approximation cannot be achieved for almost any uniformly randomly...

chapter

Regularization and Suboptimal Solutions in Learning from Data

Giorgio Gnecco, Marcello Sanguineti

Studies in Computational Intelligence > Innovations in Neural Information Paradigms and Applications > 113-154

Supervised learning from data is investigated from an optimization viewpoint. Ill-posedness issues of the learning problem are discussed and its Tikhonov, Ivanov, Phillips, and Miller regularizations are analyzed. Theoretical features of the optimization problems associated with these regularization techniques and their use in learning tasks are considered. Weight-decay learning is investigated, too...

chapter

Estimates of Approximation Rates by Gaussian Radial-Basis Functions

Paul C. Kainen, Věra Kůrková, Marcello Sanguineti

Lecture Notes in Computer Science > Adaptive and Natural Computing Algorithms > Neural Networks > 11-18

Rates of approximation by networks with Gaussian RBFs with varying widths are investigated. For certain smooth functions, upper bounds are derived in terms of a Sobolev-equivalent norm. Coefficients involved are exponentially decreasing in the dimension. The estimates are proven using Bessel potentials as auxiliary approximating functions.

chapter

Bounds for Approximate Solutions of Fredholm Integral Equations Using Kernel Networks

Giorgio Gnecco, Věra Kůrková, Marcello Sanguineti

Lecture Notes in Computer Science > Artificial Neural Networks and Machine Learning – ICANN 2011 > 126-133

Approximation of solutions of integral equations by networks with kernel units is investigated theoretically. There are derived upper bounds on speed of decrease of errors in approximation of solutions of Fredholm integral equations by kernel networks with increasing numbers of units. The estimates are obtained for Gaussian and degenerate kernels.

chapter

On Tractability of Neural-Network Approximation

Paul C. Kainen, Věra Kůrková, Marcello Sanguineti

Lecture Notes in Computer Science > Adaptive and Natural Computing Algorithms > Neural Networks > 11-21

The tractability of neural-network approximation is investigated. The dependence of worst-case errors on the number of variables is studied. Estimates for Gaussian radial-basis-function and perceptron networks are derived.

chapter

Tight Bounds on Rates of Neural-Network Approximation

Věra Kůrková, Marcello Sanguineti

Lecture Notes in Computer Science > Artificial Neural Networks — ICANN 2001 > Theory > 277-282

Complexity of neural networks measured by the number of hidden units is studied in terms of rates of approximation. Limitations of improvements of upper bounds of the order of O(n ^1/2) on such rates are investigated for perceptron networks with some periodic and sigmoidal activation functions.

chapter

Smooth Optimal Decision Strategies for Static Team Optimization Problems and Their Approximations

Giorgio Gnecco, Marcello Sanguineti

Lecture Notes in Computer Science > SOFSEM 2010: Theory and Practice of Computer Science > Regular Papers > 440-451

Sufficient conditions for the existence and uniqueness of smooth optimal decision strategies for static team optimization problems with statistical information structure are derived. Approximation methods and algorithms to derive suboptimal solutions based on the obtained results are investigated. The application to network team optimization problems is discussed.

chapter

Some Comparisons of Model Complexity in Linear and Neural-Network Approximation

Giorgio Gnecco, Věra Kůrková, Marcello Sanguineti

Lecture Notes in Computer Science > Artificial Neural Networks – ICANN 2010 > Computational Intelligence > 358-367

Capabilities of linear and neural-network models are compared from the point of view of requirements on the growth of model complexity with an increasing accuracy of approximation. Upper bounds on worst-case errors in approximation by neural networks are compared with lower bounds on these errors in linear approximation. The bounds are formulated in terms of singular numbers of certain operators induced...

chapter

Geometric Rates of Approximation by Neural Networks

Věra Kůrková, Marcello Sanguineti

Lecture Notes in Computer Science > SOFSEM 2008: Theory and Practice of Computer Science > Computing by Nature > 541-550

Model complexity of feedforward neural networks is studied in terms of rates of variable-basis approximation. Sets of functions, for which the errors in approximation by neural networks with n hidden units converge to zero geometrically fast with increasing number n, are described. However, the geometric speed of convergence depends on parameters, which are specific for each function to be approximated...

article

Supervised and semi-supervised classifiers for the detection of flood-prone areas

Giorgio Gnecco, Rita Morisi, Giorgio Roth, Marcello Sanguineti, more

Soft Computing > 2017 > 21 > 13 > 3673-3685

Supervised and semi-supervised machine-learning techniques are applied and compared for the recognition of the flood hazard. The learning goal consists in distinguishing between flood-exposed and marginal-risk areas. Kernel-based binary classifiers using six quantitative morphological features, derived from data stored in digital elevation models, are trained to model the relationship between morphology...

article

Model complexities of shallow networks representing highly varying functions

Věra Kůrková, Marcello Sanguineti

Neurocomputing > 2016 > 171 > C > 598-604

Model complexities of shallow (i.e., one-hidden-layer) networks representing highly varying multivariable {−1,1}-valued functions are studied in terms of variational norms tailored to dictionaries of network units. It is shown that bounds on these norms define classes of functions computable by networks with constrained numbers of hidden units and sizes of output weights. Estimates of probabilistic...

chapter

A multimodal dataset for the analysis of movement qualities in karate martial art

Ksenia Kolykhalova, Antonio Camurri, Gualtiero Volpe, Marcello Sanguineti, more

2015 7th International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN) > 74 - 78

2015 7th International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN)

A multimodal dataset is presented, which has been collected for analyzing and measuring the quality of movement performed during sport activities. Martial arts (namely karate) are taken as test-beds for investigation. Karate encompasses predefined sequences of movements (“katas”) that can be carried out with different qualities, e.g., by performers at different skill levels (highly vs. poorly skilled)...

article

Learning With Mixed Hard/Soft Pointwise Constraints

Giorgio Gnecco, Marco Gori, Stefano Melacci, Marcello Sanguineti

IEEE Transactions on Neural Networks and Learning Systems > 2015 > 26 > 9 > 2019 - 2032

A learning paradigm is proposed and investigated, in which the classical framework of learning from examples is enhanced by the introduction of hard pointwise constraints, i.e., constraints imposed on a finite set of examples that cannot be violated. Such constraints arise, e.g., when requiring coherent decisions of classifiers acting on different views of the same pattern. The classical examples...

chapter

Online learning as an LQG optimal control problem with random matrices

Giorgio Gnecco, Alberto Bemporad, Marco Gori, Rita Morisi, more

2015 European Control Conference (ECC) > 2482 - 2489

2015 European Control Conference (ECC)

In this paper, we combine optimal control theory and machine learning techniques to propose and solve an optimal control formulation of online learning from supervised examples, which are used to learn an unknown vector parameter modeling the relationship between the input examples and their outputs. We show some connections of the problem investigated with the classical LQG optimal control problem,...

article

Narrowing the Search for Optimal Call-Admission Policies Via a Nonlinear Stochastic Knapsack Model

Marco Cello, Giorgio Gnecco, Mario Marchese, Marcello Sanguineti

Journal of Optimization Theory and Applications > 2015 > 164 > 3 > 819-841

Call admission control with two classes of users is investigated via a nonlinear stochastic knapsack model. The feasibility region represents the subset of the call space, where given constraints on the quality of service have to be satisfied. Admissible strategies are searched for within the class of coordinate-convex policies. Structural properties that the optimal policies belonging to such a class...

Publication date

Set your own date range

Content availability

Available (50)
None (1)

Publication type

article (38)
book (13)

INFONA - science communication portal

Search results for: Marcello Sanguineti

Braess' paradox: A cooperative game‐theoretic point of view

Some properties of transportation network cooperative games

Neural approximations in discounted infinite-horizon stochastic optimal control problems

An approach to transportation network analysis via transferable utility games

Commitment-Based Equilibrium Environmental Strategies Under Time-Dependent Absorption Efficiency

Probabilistic lower bounds for approximation by shallow perceptron networks

Regularization and Suboptimal Solutions in Learning from Data

Estimates of Approximation Rates by Gaussian Radial-Basis Functions

Bounds for Approximate Solutions of Fredholm Integral Equations Using Kernel Networks

On Tractability of Neural-Network Approximation

Tight Bounds on Rates of Neural-Network Approximation

Smooth Optimal Decision Strategies for Static Team Optimization Problems and Their Approximations

Some Comparisons of Model Complexity in Linear and Neural-Network Approximation

Geometric Rates of Approximation by Neural Networks

Supervised and semi-supervised classifiers for the detection of flood-prone areas

Model complexities of shallow networks representing highly varying functions

A multimodal dataset for the analysis of movement qualities in karate martial art

Learning With Mixed Hard/Soft Pointwise Constraints

Online learning as an LQG optimal control problem with random matrices

Narrowing the Search for Optimal Call-Admission Policies Via a Nonlinear Stochastic Knapsack Model

Filter options

Publication date

Content availability

Publication type

Keywords

Data set

Journal

INFONA - science communication portal

Search results for: Marcello Sanguineti

Add recipient

Sending message cancelled

Are you sure you want to cancel sending this message?

Send message

Filter options

Publication date

Date range setting

Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.

Content availability

Publication type

Keywords

Data set

Journal

Reporting an error / abuse

Sending the report failed

Accessibility options