**Claudio Gentile's main research
activity**

**Selected publications and working papers**

**Homepages of recent co-authors and students**

**Professional activities**

- Program chair: Colt 2007, Alt 2015
- Main program commitees/area chairing: Colt 2001, Alt 2002, Alt 2005, Colt 2006, Alt 2007, ECML/PKDD 2008, IJCAI 2009, Colt 2009, Alt 2009, Colt 2011, IJCAI 2011, Colt 2012, SIAM ICDM 2012, Alt 2012, ECML/PKDD 2012, Colt 2013, IJCAI 2013, Alt 2013, Colt 2014, Alt 2014, NIPS 2014, Colt 2015, Colt 2016, ECML/PKDD 2016, NIPS 2016, Colt 2017, NIPS 2017, Colt 2018, Alt 2018, ICML 2018.
- Editorship:
- Editor (with K. Chaudhury) of the special issue of Theoretical Computer Science on Alt 2015
- Editor (with N. Bshouty) of the special issue of Machine Learning Journal on Colt2007. Guest editors' introduction
- Member of the editorial board of Machine Learning journal
- Member of the editorial board of Journal of Machine Learning Research
- Editor of the special issue of Machine Learning Journal on Colt2001. Guest editor's introduction

**Research projects****Current****Online clustering while exploring and exploiting**

Supported by Criteo through a Faculty Research Award.

**Past****BASC Project**

MIUR.**PASCAL 2 Network of Excellence**

EU, Seventh Programme Framework.**Data-dependent geometries and structures**

("pump-priming project" within Pascal2).**PASCAL Network of Excellence**

EU, Sixth Programme Framework.**Kermit**

EU, Fifth Programme Framework.**Neurocolt II**

EU, Fourth Programme Framework.

**Useful links**### Conferences

- 31st Annual Conference on Learning Theory (COLT 2018)
- 35th International Conference on Machine Learning (ICML 2018)
- Neural Information Processing Systems (NIPS)

### Journals

- IEEE: Transactions on Information Theory
- IEEE Transactions on Neural Networks
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Information and Computation
- Journal of the ACM
- Journal of Computer and System Sciences
- Journal of Machine Learning Research
- Machine Learning
- Neural Computation
- Pattern Recognition

### Other links

- Boosting research site
- COLT: Computational Learning Theory
- IEEE Neural Networks Society home page
- The collection of Computer Science bibliographies

**Selected publications and working papers**

These publications and working papers are listed roughly in reverse chronological order of their initial publication date.

**Working papers****On Similarity Prediction and Pairwise Clustering**

with S. Pasteris, F. Vitale, M. Herbster, ALT 2018, to appear.**Measures to Address the Lack of Portability of the RF Fingerprints for Radiometric Identification**

with G. Baldini, R. Giuliani, G. Steri, and I. Sanchez, NTMS 2018, to appear.**The Application of the Symbolic Aggregate Approximation Algorithm (SAX) to Radio Frequency Fingerprinting of IoT Devices**

with G. Baldini, R. Giuliani, and G. Steri, SCVT 2017, to appear.**Boltzmann Exploration Done Right**

with G. Neu, N. Cesa-Bianchi, G. Lugosi, NIPS 2017, to appear.

**Selected publications****Imaging time series for the identification of IoT devices through RF fingerprinting**

with with G. Baldini, G. Steri, and R. Giuliani

Proc. of the 51st International Carnahan Conference on Security Technology (ICCST 2017), to appear.**On Context-Dependent Clustering of Bandits (Main, Supplemental)**

with S. Li, A. Karatzoglou, P. Kar, E. Etrue, G. Zappella

Proc. of the 34th International Conference on Machine Learning (ICML 2017).**Algorithmic chaining and the role of partial feedback in online nonparametric learning (Short version, Long version)**

with N. Cesa-Bianchi, P. Gaillard, S. Gerchinovitz

Proc. of the 30th Annual Conference on Learning Theory (COLT 2017).**Identification of mobile phones using the built-in magnetometers stimulated by motion patterns**

with G. Baldini, F. Dimc, R. Kamnik, G. Steri, and R. Giuliani*Sensors*, 17, 783, 2017.**On the Troll-Trust Model for Edge Sign Prediction in Social Networks (Main, Supplemental)**

with G. Le Falher, N. Cesa-Bianchi, F. Vitale

Proc. of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017).**Delay and Cooperation in Nonstochastic Bandits**

with N. Cesa-Bianchi, Y. Mansour, A. Minora

Proc. of the 29th Annual Conference on Learning Theory (COLT 2016).

Long version submitted for journal publication.**Collaborative Filtering Bandits**

with S. Li, A. Karatzoglou

Proc. of the 39th ACM Conference on Research and Development in Information Retrieval (SIGIR 2016).**Online Clustering of Bandits (Main, Supplemental)**

with S. Li and G. Zappella

Proc. of the 31st International Conference on Machine Learning (ICML 2014).**From Bandits to Experts: A Tale of Domination and Independence**

with N. Alon, N. Cesa-Bianchi, Y. Mansour

Proc. of the 27th conference on Neural Information Processing Systems (NIPS 2013).

Long version (also with O. Shamir and S. Mannor),*SIAM Journal on Computing*, 46/6 (2017), pp. 1785--1826.**A gang of Bandits (Main, Supplemental)**

with N. Cesa-Bianchi, G. Zappella

Proc. of the 27th conference on Neural Information Processing Systems (NIPS 2013).**Online Similarity Prediction of Networked Data from Known and Unknown Graphs**

with M. Herbster, S. Pasteris

Proc. of the 26th Conference on Learning Theory (COLT 2013).**Regret Minimization for Branching Experts**

with E. Gofer, N. Cesa-Bianchi, Y. Mansour

Proc. of the 26th Conference on Learning Theory (COLT 2013).**Regret Minimization for Reserve Prices in Second-Price Auctions**

with N. Cesa-Bianchi, Y. Mansour*IEEE Trans. on Information Theory*, 61/1 (2015), pp. 549--564.

Preliminary version in Proc. of the 24th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2013), pp 1190-1204.

Slides of the talk given at SODA 2013.**On multilabel classification and ranking with bandit feedback**

with F. Orabona*Journal of Machine Learning Research*, 15 (2014), pp. 2451--2487.

Preliminary version in Proc. of the 26th conference on Neural Information processing Systems (NIPS 2012).**A linear time active learning algorithm for link classification**

with N. Cesa-Bianchi, F. Vitale, G. Zappella

Proc. of the 26th conference on Neural Information processing Systems (NIPS 2012).**A Correlation Clustering Approach to Link Classification in Signed Networks**

with N. Cesa-Bianchi, F. Vitale, G. Zappella

Proc. of the 25th Conference on Learning Theory (COLT 2012).**Beyond logarithmic bounds in online learning**

with F. Orabona, N. Cesa-Bianchi

Proc. of the 15th International Conference on Artificial Intelligence and Statistics (Aistats 2012).**See the tree through the lines: the Shazoo algorithm**

with N. Cesa-Bianchi, F. Vitale, G. Zappella

Proc. of the 25th conference on Neural Information processing Systems (NIPS 2011).**Multiclass classification with bandit feedback using adaptive regularization**

with K. Crammer*Machine Learning*, 90/3 (2013), pp. 347-383.

Preliminary version in Proc. of the 28th International Conference on Machine Learning (ICML 2011).

Video recorded presentation at ICML 2011.**Selective sampling and active learning from single and multiple teachers**

with O. Dekel, K. Sridharan*Journal of Machine Learning Research*, 13 (2012), pp. 2655--2697.

Preliminary version in Proc. of the 23rd Conference on Learning Theory (COLT 2010).**Active learning on trees and graphs**

with N. Cesa-Bianchi, F. Vitale, G. Zappella

Proc. of the 23rd Conference on Learning Theory (COLT 2010).**Random spanning trees and the prediction of weighted graphs**

with N. Cesa-Bianchi, F. Vitale, G. Zappella*Journal of Machine Learning Research*, 14 (2013), pp. 1251--1284.

Preliminary version in Proc. of the 27th International Conference on Machine Learning (ICML 2010).**Predicting the labels of an unknown graph via adaptive exploration**

with N. Cesa-Bianchi, F, Vitale

*Theoretical Computer Science*, special issue on Algorithmic Learning Theory, 412/19 (2011), pp. 1791--1804.

Preliminary version in

Proc. of the 20th International conference on Algorithmic Learning Theory (Alt 2009), pp. 110-125.**Fast and optimal prediction of a labeled tree**

with N. Cesa-Bianchi, F. Vitale

Proc. of of the 22nd Conference on Learning Theory (COLT 2009).**Robust bounds for classification via selective sampling**

with N. Cesa-Bianchi, F. Orabona

Proc. of the 26th International Conference on Machine Learning (ICML 2009).**Learning Noisy Linear Classifiers via Adaptive and Selective Sampling**

with G. Cavallanti, N. Cesa-Bianchi*Machine Learning*, 83 (2011), pp. 71-102.

Preliminary version in

Proc. of the 22nd conference on Neural Information processing Systems (NIPS 2008).

Poster presentation at NIPS 2008, December 2008.**Linear algorithms for online multitask classification**

with G. Cavallanti, N. Cesa-Bianchi*Journal of Machine Learning Research*, 11 (2010), pp. 2901--2934.

Preliminary version in

Proc. of the 21st Conference on Learning Theory (COLT'08).

Presentation at the Workshop on Learning Theory at FoCM 2008, June 2008.**On higher-order Perceptron algorithms**

with C. Brotto, F. Vitale

Proc. of the 21st conference on Neural Information processing Systems (NIPS 2007).

Poster presentation at NIPS 2007, December 2007.**Hierarchical Classification: Combining Bayes with SVM**

with N. Cesa-Bianchi, L. Zaniboni

Proc. of the 23rd International Conference on Machine Learning (ICML 2006), pages 177--184.

Slides of a talk given at University College London, July 2006.**Tracking the best hyperplane with a simple budget perceptron**

with G. Cavallanti, N. Cesa-Bianchi*Machine Learning*, 69/2-3 (2007),

special issue on COLT 2006, pp. 143--167.

Preliminary version in

Proc. of the 19th annual Conference on Learning Theory (COLT'06), pages 483--496.**Improved risk tail bounds for on-line algorithms**

with N. Cesa-Bianchi*IEEE Trans. on Information Theory*, 54/1 (2008), pp. 386--390.

Preliminary version in

Proc. of the 18th conference on Neural Information processing Systems (NIPS 2005).**Incremental algorithms for hierarchical classification**

with N. Cesa-Bianchi, L. Zaniboni*Journal of Machine Learning Research*, 7 (2006), pp. 31--54.

Preliminary version in

Proc. of the 17th conference on Neural Information processing Systems (NIPS 2004).**Worst-Case Analysis of Selective sampling for linear-threshold algorithms**

with N. Cesa-Bianchi, L. Zaniboni*Journal of Machine Learning Research*, 7 (2006), pp. 1205--1230.

Preliminary version in

Proc. of the 17th conference on Neural Information processing Systems (NIPS 2004).**Regret bounds for hierarchical classification with linear-threshold functions**

with N. Cesa-Bianchi, A. Conconi

Proc. of the 17th annual Conference on Learning Theory (COLT'04), pp. 93-108.

Slides of the talk given at Colt'04.**Fast feature selection from microarray expression data via multiplicative large margin algorithms**

Proc. of the 16th conference on Neural Information processing Systems (NIPS 2003).

Slides of a talk given at University of Modena, Dec 2004.

Datasets used in the experiments (5.8 MB).**Learning probabilistic linear-threshold classifiers via selective sampling**

with N. Cesa-Bianchi, A. Conconi

Proc. of the 16th annual Conference on Learning Theory (COLT'03), pp. 373-387.**Margin-based algorithms for information filtering**

with N. Cesa-Bianchi, A. Conconi

Proc. of the 15th conference on Neural Information processing Systems (NIPS 2002), pp. 470-477.**A second-order perceptron algorithm**

with N. Cesa-Bianchi, A. Conconi,*SIAM Journal on Computing*, 34/3 (2005), pp. 640-668.

Preliminary version in

Proc. of the 15th annual conference on Computational Learning Theory (COLT'02), pp. 121-137.

Slides of the talk given at COLT'02.**On the generalization ability of on-line learning algorithms**

with N. Cesa-Bianchi, A. Conconi,*IEEE Trans. on Information Theory*, 50/9 (2004), pp. 2050-2057.

Preliminary version in

Proc. of the 14th conference on Neural Information processing Systems (NIPS 2001)**A new approximate maximal margin classification algorithm***Journal of Machine Learning Research*2 (2002), pp. 213-242.

Preliminary version in Proc. of the 13th conference on Neural Information processing Systems (NIPS 2000).

A Matlab implementation of the algorithm (with kernels) can be found, e.g., here.**Adaptive and self-confident on-line learning algorithms**

with P. Auer, N. Cesa-Bianchi,*Journal of Computer and System Sciences*, 64/1 (2002),

special issue on Computational Learning Theory, pp. 48-75.

Preliminary version in

Proc. of the 13th annual conference on Computational Learning Theory (COLT'00), pp. 107-117.

Slides of the talk given at COLT'00.**The robustness of the p-norm algorithms***Machine Learning*, 53/3 (2003), pp. 265-299.

Preliminary version (with N. Littlestone) in

Proc. of the 12th annual ACM conference on Computational Learning Theory (COLT'99), pp. 1-11.**Linear hinge loss and average margin**

with M. Warmuth

in Proc. of the 11th conference on Neural Information processing Systems (NIPS 1998), pp. 225-231.**Improved lower bounds for learning from noisy examples: an information-theoretic approach**

with D. Helmbold*Information and Computation*166/2 (2001), pp. 133-155.

Preliminary version in

Proc. of the 11th annual ACM conference on Computational Learning Theory (COLT'98), pp. 104-115.**P-sufficient statistics for PAC learning k-term-DNF formulas through enumeration**

with B. Apolloni*Theoretical Computer Science*230 (2000), pp. 1-37.**Sample size lower bounds in PAC learning by algorithmic complexity theory**

with B. Apolloni*Theoretical Computer Science*209 (1998), pp. 141-162.

**All publications****All publications**(as of June 2017)

**Homepages of recent co-authors and students (under construction...)** **Fabio Vitale****Shuai Li**