Sandro Ridella

115 papers A 1B 37C 3Journal 60Unranked 14

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Reconciling grokking with statistical learning theory through the lens of norm- and stability-based generalization bounds. Neurocomputing Luca Oneto, Sandro Ridella, Simone Minisi, Andrea Coraddu, Davide Anguita
2025	J	`jnl`	Informed Machine Learning: Excess risk and generalization. Neurocomputing Luca Oneto, Sandro Ridella, Davide Anguita
2024	B	`conf`	Informed Machine Learning: Excess Risk and Generalization. ESANN Luca Oneto, Davide Anguita, Sandro Ridella
2024	J	`jnl`	Towards algorithms and models that we can trust: A theoretical perspective. Neurocomputing Luca Oneto, Sandro Ridella, Davide Anguita
2023	J	`jnl`	Do we really need a new theory to understand over-parameterization? Neurocomputing Luca Oneto, Sandro Ridella, Davide Anguita
2023	B	`conf`	Towards Randomized Algorithms and Models that We Can Trust: a Theoretical Perspective. ESANN Luca Oneto, Sandro Ridella, Davide Anguita
2022	B	`conf`	Do We Really Need a New Theory to Understand the Double-Descent? ESANN Luca Oneto, Sandro Ridella, Davide Anguita
2022	J	`jnl`	The benefits of adversarial defense in generalization. Neurocomputing Luca Oneto, Sandro Ridella, Davide Anguita
2021	J	`jnl`	Distribution-Dependent Weighted Union Bound. Entropy Luca Oneto, Sandro Ridella
2021	B	`conf`	The Benefits of Adversarial Defence in Generalisation. ESANN Luca Oneto, Sandro Ridella, Davide Anguita
2020	B	`conf`	Improving the Union Bound: a Distribution Dependent Approach. ESANN Luca Oneto, Sandro Ridella, Davide Anguita
2019	J	`jnl`	Local Rademacher Complexity Machine. Neurocomputing Luca Oneto, Sandro Ridella, Davide Anguita
2018	J	`jnl`	Learning With Kernels: A Local Rademacher Complexity-Based Analysis With Application to Graph Kernels. IEEE Trans. Neural Networks Learn. Syst. Luca Oneto, Nicolò Navarin, Michele Donini, Sandro Ridella, Alessandro Sperduti, Fabio Aiolli, Davide Anguita
2018	B	`conf`	Local Rademacher Complexity Machine. ESANN Luca Oneto, Sandro Ridella, Davide Anguita
2018	J	`jnl`	Randomized learning: Generalization performance of old and new theoretically grounded algorithms. Neurocomputing Luca Oneto, Francesca Cipollini, Sandro Ridella, Davide Anguita
2017	J	`jnl`	Differential privacy and generalization: Sharper bounds with applications. Pattern Recognit. Lett. Luca Oneto, Sandro Ridella, Davide Anguita
2017	B	`conf`	Generalization Performances of Randomized Classifiers and Algorithms built on Data Dependent Distributions. ESANN Luca Oneto, Sandro Ridella, Davide Anguita
2016	J	`jnl`	A local Vapnik-Chervonenkis complexity. Neural Networks Luca Oneto, Davide Anguita, Sandro Ridella
2016	J	`jnl`	Global Rademacher Complexity Bounds: From Slow to Fast Convergence Rates. Neural Process. Lett. Luca Oneto, Alessandro Ghio, Sandro Ridella, Davide Anguita
2016	J	`jnl`	Learning Hardware-Friendly Classifiers Through Algorithmic Stability. ACM Trans. Embed. Comput. Syst. Luca Oneto, Sandro Ridella, Davide Anguita
2016	J	`jnl`	PAC-bayesian analysis of distribution dependent priors: Tighter risk bounds and stability analysis. Pattern Recognit. Lett. Luca Oneto, Davide Anguita, Sandro Ridella
2016	J	`jnl`	Tikhonov, Ivanov and Morozov regularization for support vector machine learning. Mach. Learn. Luca Oneto, Sandro Ridella, Davide Anguita
2016	B	`conf`	Tuning the Distribution Dependent Prior in the PAC-Bayes Framework based on Empirical Data. ESANN Luca Oneto, Sandro Ridella, Davide Anguita
2015	B	`conf`	Fast convergence of extended Rademacher Complexity bounds. IJCNN Luca Oneto, Alessandro Ghio, Sandro Ridella, Davide Anguita
2015	J	`jnl`	Fully Empirical and Data-Dependent Stability-Based Bounds. IEEE Trans. Cybern. Luca Oneto, Alessandro Ghio, Sandro Ridella, Davide Anguita
2015	J	`jnl`	Learning Resource-Aware Classifiers for Mobile Devices: From Regularization to Energy Efficiency. Neurocomputing Luca Oneto, Alessandro Ghio, Sandro Ridella, Davide Anguita
2015	J	`jnl`	Local Rademacher Complexity: Sharper risk bounds with and without unlabeled samples. Neural Networks Luca Oneto, Alessandro Ghio, Sandro Ridella, Davide Anguita
2015	B	`conf`	Shrinkage learning to improve SVM with hints. IJCNN Luca Oneto, Alessandro Ghio, Sandro Ridella, Davide Anguita
2015	B	`conf`	Support vector machines and strictly positive definite kernel: The regularization hyperparameter is more important than the kernel hyperparameters. IJCNN Luca Oneto, Alessandro Ghio, Sandro Ridella, Davide Anguita
2014	J	`jnl`	A Deep Connection Between the Vapnik-Chervonenkis Entropy and the Rademacher Complexity. IEEE Trans. Neural Networks Learn. Syst. Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2014	B	`conf`	Learning with few bits on small-scale devices: From regularization to energy efficiency. ESANN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2014	—	`conf`	Out-of-Sample Error Estimation: The Blessing of High Dimensionality. ICDM Workshops Luca Oneto, Alessandro Ghio, Sandro Ridella, Jorge Luis Reyes-Ortiz, Davide Anguita
2014	B	`conf`	Smartphone battery saving by bit-based hypothesis spaces and local Rademacher Complexities. IJCNN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2014	J	`jnl`	Unlabeled patterns to tighten Rademacher complexity error bounds for kernel classifiers. Pattern Recognit. Lett. Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2013	B	`conf`	A Learning Machine with a Bit-Based Hypothesis Space. ESANN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2013	C	`conf`	A Novel Procedure for Training L1-L2 Support Vector Machine Classifiers. ICANN Davide Anguita, Alessandro Ghio, Luca Oneto, Jorge Luis Reyes-Ortiz, Sandro Ridella
2013	J	`jnl`	A Survey of old and New Results for the Test Error Estimation of a Classifier. J. Artif. Intell. Soft Comput. Res. Davide Anguita, Luca Ghelardoni, Alessandro Ghio, Sandro Ridella
2013	B	`conf`	A support vector machine classifier from a bit-constrained, sparse and localized hypothesis space. IJCNN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2013	J	`jnl`	An improved analysis of the Rademacher data-dependent bound using its self bounding property. Neural Networks Luca Oneto, Alessandro Ghio, Davide Anguita, Sandro Ridella
2013	B	`conf`	Some results about the Vapnik-Chervonenkis entropy and the rademacher complexity. IJCNN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2012	J	`jnl`	In-Sample and Out-of-Sample Model Selection and Error Estimation for Support Vector Machines. IEEE Trans. Neural Networks Learn. Syst. Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2012	J	`jnl`	In-sample Model Selection for Trimmed Hinge Loss Support Vector Machine. Neural Process. Lett. Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2012	J	`jnl`	Learning the mean: A neural network approach. Neurocomputing Sergio Decherchi, Mauro Parodi, Sandro Ridella
2012	—	`conf`	Nested Sequential Minimal Optimization for Support Vector Machines. ICANN (2) Alessandro Ghio, Davide Anguita, Luca Oneto, Sandro Ridella, Carlotta Schatten
2012	—	`conf`	Rademacher Complexity and Structural Risk Minimization: An Application to Human Gene Expression Datasets. ICANN (2) Luca Oneto, Davide Anguita, Alessandro Ghio, Sandro Ridella
2012	B	`conf`	Structural Risk Minimization and Rademacher Complexity for Regression. ESANN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2012	B	`conf`	The 'K' in K-fold Cross Validation. ESANN Davide Anguita, Luca Ghelardoni, Alessandro Ghio, Luca Oneto, Sandro Ridella
2011	J	`jnl`	A FPGA Core Generator for Embedded Classification Systems. J. Circuits Syst. Comput. Davide Anguita, Luca Carlino, Alessandro Ghio, Sandro Ridella
2011	B	`conf`	In-sample model selection for Support Vector Machines. IJCNN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2011	J	`jnl`	Maximal Discrepancy for Support Vector Machines. Neurocomputing Davide Anguita, Alessandro Ghio, Sandro Ridella
2011	B	`conf`	Maximal Discrepancy vs. Rademacher Complexity for error estimation. ESANN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2011	B	`conf`	Selecting the hypothesis space for improving the generalization ability of Support Vector Machines. IJCNN Davide Anguita, Alessandro Ghio, Luca Oneto, Sandro Ridella
2011	—	`conf`	Test error bounds for classifiers: A survey of old and new results. FOCI Davide Anguita, Luca Ghelardoni, Alessandro Ghio, Sandro Ridella
2011	—	`conf`	The Impact of Unlabeled Patterns in Rademacher Complexity Theory for Kernel Classifiers. NIPS Luca Oneto, Davide Anguita, Alessandro Ghio, Sandro Ridella
2010	B	`conf`	A neural model approach for regularization in the mean estimation case. IJCNN Sergio Decherchi, Mauro Parodi, Sandro Ridella
2010	B	`conf`	Maximal Discrepancy for Support Vector Machines. ESANN Davide Anguita, Alessandro Ghio, Sandro Ridella
2010	B	`conf`	Model selection for support vector machines: Advantages and disadvantages of the Machine Learning Theory. IJCNN Davide Anguita, Alessandro Ghio, Noemi Greco, Luca Oneto, Sandro Ridella
2010	J	`jnl`	Using unsupervised analysis to constrain generalization bounds for support vector classifiers. IEEE Trans. Neural Networks Sergio Decherchi, Sandro Ridella, Rodolfo Zunino, Paolo Gastaldo, Davide Anguita
2009	—	`conf`	K-Fold Cross Validation for Error Rate Estimate in Support Vector Machines. DMIN Davide Anguita, Alessandro Ghio, Sandro Ridella, Dario Sterpi
2008	J	`jnl`	A support vector machine with integer parameters. Neurocomputing Davide Anguita, Alessandro Ghio, Stefano Pischiutta, Sandro Ridella
2008	B	`conf`	Using Variable Neighborhood Search to improve the Support Vector Machine performance in embedded automotive applications. IJCNN Enrique Alba, Davide Anguita, Alessandro Ghio, Sandro Ridella
2007	B	`conf`	A Hardware-friendly Support Vector Machine for Embedded Automotive Applications. IJCNN Davide Anguita, Alessandro Ghio, Stefano Pischiutta, Sandro Ridella
2006	J	`jnl`	Feed-Forward Support Vector Machine Without Multipliers. IEEE Trans. Neural Networks Davide Anguita, Stefano Pischiutta, Sandro Ridella, Dario Sterpi
2006	J	`jnl`	Prospects of quantum-classical optimization for digital design. Appl. Math. Comput. Paolo Gastaldo, Sandro Ridella, Rodolfo Zunino
2006	B	`conf`	Testing the Augmented Binary Multiclass SVM on Microarray Data. IJCNN Davide Anguita, Sandro Ridella, Dario Sterpi
2005	B	`conf`	K-fold generalization capability assessment for support vector classifiers. IJCNN Davide Anguita, Sandro Ridella, Fabio Rivieccio
2004	B	`conf`	A new method for multiclass support vector machines. IJCNN Davide Anguita, Sandro Ridella, Dario Sterpi
2004	—	`conf`	An Algorithm for Reducing the Number of Support Vectors. WIRN Davide Anguita, Sandro Ridella, Fabio Rivieccio
2004	B	`conf`	Model selection in top quark tagging with a support vector classifier. IJCNN Davide Anguita, Sandro Ridella, Silvia Amerio, Ignazio Lazzizzera
2004	B	`conf`	Unsupervised clustering and the capacity of support vector machines. IJCNN Davide Anguita, Sandro Ridella, Fabio Rivieccio, Rodolfo Zunino
2004	J	`jnl`	Using K-Winner Machines for domain analysis. Neurocomputing Sandro Ridella, Rodolfo Zunino
2004	B	`conf`	Vector quantization complexity and quantum computing. IJCNN Paolo Gastaldo, Sandro Ridella, Rodolfo Zunino
2003	J	`jnl`	A digital architecture for support vector machines: theory, algorithm, and FPGA implementation. IEEE Trans. Neural Networks Davide Anguita, Andrea Boni, Sandro Ridella
2003	B	`conf`	A model-selection approach to the VLSI design of vector quantizers. IJCNN Massimiliano Bracco, Sandro Ridella, Rodolfo Zunino
2003	J	`jnl`	Digital implementation of hierarchical vector quantization. IEEE Trans. Neural Networks Massimiliano Bracco, Sandro Ridella, Rodolfo Zunino
2003	J	`jnl`	Hyperparameter design criteria for support vector classifiers. Neurocomputing Davide Anguita, Sandro Ridella, Fabio Rivieccio, Rodolfo Zunino
2003	J	`jnl`	Quantum optimization for training support vector machines. Neural Networks Davide Anguita, Sandro Ridella, Fabio Rivieccio, Rodolfo Zunino
2003	B	`conf`	SVM learning with fixed-point math. IJCNN Davide Anguita, Andrea Boni, Sandro Ridella
2003	B	`conf`	Training support vector machines: a quantum-computing perspective. IJCNN Davide Anguita, Sandro Ridella, Fabio Rivieccio, Rodolfo Zunino
2002	C	`conf`	Automatic Hyperparameter Tuning for Support Vector Machines. ICANN Davide Anguita, Sandro Ridella, Fabio Rivieccio, Rodolfo Zunino
2001	J	`jnl`	Empirical measure of multiclass generalization performance: the K-winner machine case. IEEE Trans. Neural Networks Sandro Ridella, Rodolfo Zunino
2001	J	`jnl`	K-winner machines for pattern classification. IEEE Trans. Neural Networks Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
2000	C	`conf`	Augmenting vector quantization with interval arithmetics for image-coding applications. ISCAS Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
2000	J	`jnl`	Digital VLSI Algorithms and Architectures for Support Vector Machines. Int. J. Neural Syst. Davide Anguita, Andrea Boni, Sandro Ridella
2000	J	`jnl`	Evaluating the Generalization Ability of Support Vector Machines through the Bootstrap. Neural Process. Lett. Davide Anguita, Andrea Boni, Sandro Ridella
2000	—	`conf`	The K-Winner Machine Model. IJCNN (1) Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1999	B	`conf`	A VLSI friendly algorithm for support vector machines. IJCNN Davide Anguita, Andrea Boni, Sandro Ridella
1999	J	`jnl`	Circular backpropagation networks embed vector quantization. IEEE Trans. Neural Networks Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1999	J	`jnl`	Possibility and Necessity Pattern Classification using an Interval Arithmetic Perceptron. Neural Comput. Appl. Gian Paolo Drago, Sandro Ridella
1999	J	`jnl`	Representation and generalization properties of class-entropy networks. IEEE Trans. Neural Networks Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1999	—	`conf`	Support Vector Machines: A Comparison of Some Kernel Functions. IIA/SOCO Davide Anguita, Andrea Boni, Sandro Ridella
1999	J	`jnl`	Worst case analysis of weight inaccuracy effects in multilayer perceptrons. IEEE Trans. Neural Networks Davide Anguita, Sandro Ridella, Stefano Rovetta
1998	J	`jnl`	Plastic Algorithm for Adaptive Vector Quantisation. Neural Comput. Appl. Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1998	J	`jnl`	Pruning with interval arithmetic perceptron. Neurocomputing Gian Paolo Drago, Sandro Ridella
1997	—	`conf`	CBP networks as a generalized neural model. ICNN Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1997	J	`jnl`	Circular backpropagation networks for classification. IEEE Trans. Neural Networks Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1997	—	`conf`	On the importance of sorting in "neural gas" training of vector quantizers. ICNN Fabio Ancona, Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1996	—	`conf`	Limiting the effects of weight errors in feedforward networks using interval arithmetic. ICNN Davide Anguita, Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1996	J	`jnl`	On the convergence of a growing topology neural algorithm. Neurocomputing Gian Paolo Drago, Sandro Ridella
1995	J	`jnl`	Adaptive Internal Representation in Circular Back-Propagation Networks. Neural Comput. Appl. Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1995	J	`jnl`	An Adaptive Momentum Back Propagation (AMBP). Neural Comput. Appl. Gian Paolo Drago, Mauro Morando, Sandro Ridella
1995	B	`conf`	Learning the appropriate representation paradigm by circular processing units. ESANN Sandro Ridella, Stefano Rovetta, Rodolfo Zunino
1994	J	`jnl`	Class-Entropy Minimisation Networks for Domain Analysis and Rule Extraction. Neural Comput. Appl. Sandro Ridella, Gian Luca Speroni, Paolo Trebino, Rodolfo Zunino
1994	J	`jnl`	Convergence Properties of Cascade Correlation in Function Approximation. Neural Comput. Appl. Gian Paolo Drago, Sandro Ridella
1993	—	`conf`	Pruning and rule extraction using class entropy. ICNN Sandro Ridella, Gian Luca Speroni, Paolo Trebino, Rodolfo Zunino
1993	J	`jnl`	Using chaos to generate keys for associative noise-like coding memories. Neural Networks Giancarlo Parodi, Sandro Ridella, Rodolfo Zunino
1992	J	`jnl`	A dedicated massively parallel architecture for the Boltzmann machine. Parallel Comput. Alessandro De Gloria, Paolo Faraboschi, Sandro Ridella
1992	J	`jnl`	Global Optimization of Functions with the Interval Genetic Algorithm. Complex Syst. Marco Muselli, Sandro Ridella
1992	J	`jnl`	Statistically controlled activation weight initialization (SCAWI). IEEE Trans. Neural Networks Gian Paolo Drago, Sandro Ridella
1991	J	`jnl`	Efficient computation of the correlation dimension from a time series on a LIW computer. Parallel Comput. Angelo Corana, Aldo Casaleggio, Claudia Rolando, Sandro Ridella
1989	J	`jnl`	Corrigenda: "Minimizing Multimodal Functions of Continuous Variables with the 'Simulated Annealing' Algorithm". ACM Trans. Math. Softw. Angelo Corana, Claudio Martini, Sandro Ridella
1988	J	`jnl`	Solving linear equation systems on vector computers with maximum efficiency. Parallel Comput. A. Corona, Claudio Martini, Mauro Morando, Sandro Ridella, Claudia Rolando
1987	A	`conf`	LU Factorization with Maximum Performances on FPS Architectures 38/64 BIT. ICS Angelo Corana, Claudio Martini, Sandro Ridella, Claudia Rolando
1987	J	`jnl`	Minimizing multimodal functions of continuous variables with the "simulated annealing" algorithm. ACM Trans. Math. Softw. Angelo Corana, Michele Marchesi, Claudio Martini, Sandro Ridella
1986	—	`conf`	Caltech Hypercube MIMD Computer Performances Measurements in a Physical Mathematical Application. CONPAR Claudio Martini, Mauro Morando, Sandro Ridella