25,161
edits
Changes
Created page with "'''Home * People * Nicolò Cesa-Bianchi''' FILE:nicolocesabianchi.jpg|border|right|thumb|link=https://scholar.google.com/citations?user=BWADJUkAAAAJ&hl=en..."
'''[[Main Page|Home]] * [[People]] * Nicolò Cesa-Bianchi'''
[[FILE:nicolocesabianchi.jpg|border|right|thumb|link=https://scholar.google.com/citations?user=BWADJUkAAAAJ&hl=en| Nicolò Cesa-Bianchi <ref>[https://scholar.google.com/citations?user=BWADJUkAAAAJ&hl=en Nicolò Cesa-Bianchi - Google Scholar Citations]</ref> ]]
'''Nicolò Cesa-Bianchi''',<br/>
an Italian computer scientist and professor at department of computer science, [https://en.wikipedia.org/wiki/University_of_Milan University of Milan]. His research interests include a wide range in the fields of [[Learning|machine learning]] and [https://en.wikipedia.org/wiki/Computational_learning_theory computational learning theory], such as [[Reinforcement Learning|reinforcement learning]], [https://en.wikipedia.org/wiki/Game_theory game-theoretic] learning, [https://en.wikipedia.org/wiki/Statistical_learning_theory statistical learning theory], [https://en.wikipedia.org/wiki/Prediction prediction] with expert advice, and [https://en.wikipedia.org/wiki/Multi-armed_bandit bandit problems]. Along with [[Gábor Lugosi]], he authored ''Prediction, Learning, and Games'' in 2006 <ref>[[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2006'''). ''[http://homes.di.unimi.it/cesa-bianchi/predbook/ Prediction, Learning, and Games]''. [https://en.wikipedia.org/wiki/Cambridge_University_Press Cambridge University Press]
"...beware of mathematicians, and all those who make empty prophecies. The danger already exists that the mathematicians have made a covenant with the devil to darken the spirit and to confine man in the bonds of Hell". [https://en.wikipedia.org/wiki/Augustine_of_Hippo St. Augustine], [http://www.augustinus.it/latino/genesi_lettera/genesi_lettera_02.htm De Genesi ad Litteram libri duodecim. Liber Secundus, 17, 37.]</ref>.
=Bandit Problems=
In [https://en.wikipedia.org/wiki/Probability_theory probability theory], the [https://en.wikipedia.org/wiki/Multi-armed_bandit multi-armed bandit problem] faces the tradeoff between [https://en.wikipedia.org/wiki/Exploitation_%28disambiguation%29 exploitation] of the [https://en.wikipedia.org/wiki/Slot_machine slot machine] that has the highest expected payoff and [https://en.wikipedia.org/wiki/Exploration exploration] to get more information about the expected payoffs of the other machines. The trade-off between exploration and exploitation is also topic in [[Reinforcement Learning|reinforcement learning]] <ref>[https://en.wikipedia.org/wiki/Multi-armed_bandit Multi-armed bandit from Wikipedia]</ref>. The [https://en.wikipedia.org/wiki/Gambling gambler] has to decide at time steps t = 1, 2, ... which of the finitely many available arms to pull. Each arm produces a [https://en.wikipedia.org/wiki/Reward reward] in a [https://en.wikipedia.org/wiki/Stochastic stochastic] manner. The goal is to maximize the reward accumulated over time. In 2002, along with [[Peter Auer]] and [[Paul Fischer]], Nicolò Cesa-Bianchi introduced the '''UCB1''' (Upper Confidence Bounds) bandit algorithm <ref>[[Peter Auer]], [[Nicolò Cesa-Bianchi]], [[Paul Fischer]] ('''2002'''). ''[http://link.springer.com/article/10.1023%2FA%3A1013689704352 Finite-time Analysis of the Multiarmed Bandit Problem]''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 47, No. 2, [http://homes.di.unimi.it/~cesabian/Pubblicazioni/ml-02.pdf pdf]</ref>, which was applied as selection algorithm [[UCT]] to [[Monte-Carlo Tree Search]] as elaborated by [[Levente Kocsis]] and [[Csaba Szepesvári]] in 2006 <ref>[[Levente Kocsis]], [[Csaba Szepesvári]] ('''2006'''). ''[http://www.computer-go.info/resources/bandit.html Bandit based Monte-Carlo Planning]'' ECML-06, LNCS/LNAI 4212, [http://www.sztaki.hu/%7Eszcsaba/papers/ecml06.pdf pdf]</ref>.
=Selected Publications=
<ref>[http://dblp.uni-trier.de/pers/hd/c/Cesa=Bianchi:Nicol=ograve= dblp: Nicolò Cesa-Bianchi]</ref> <ref>[http://homes.di.unimi.it/cesa-bianchi/papers.html Nicolò Cesa-Bianchi - Selected papers:]</ref>
==1990 ...==
* [[Nicolò Cesa-Bianchi]] ('''1990'''). ''Learning the Distribution in the Extended PAC Model''. [http://dblp.uni-trier.de/db/conf/alt/alt1990.html#Cesa-Bianchi90 ALT 1990]
* [[Peter Auer]], [[Nicolò Cesa-Bianchi]] ('''1994'''). ''On-line learning with malicious noise and the closure algorithm''. [http://www.springer.com/gp/book/9783540585206 Algorithmic Learning Theory], [https://en.wikipedia.org/wiki/Lecture_Notes_in_Computer_Science LNAI], [https://en.wikipedia.org/wiki/Springer_Science%2BBusiness_Media Springer]
* [[Nicolò Cesa-Bianchi]], [[Yoav Freund]], [[Mathematician#DPHelmbold|David P. Helmbold]], [[Mathematician#MKWarmuth|Manfred K. Warmuth]] ('''1996'''). ''On-line Prediction and Conversion Strategies''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 25, No 1, [http://homes.di.unimi.it/cesa-bianchi/Pubblicazioni/ml-96.pdf pdf]
* [[Nicolò Cesa-Bianchi]], [[Yoav Freund]], [[Mathematician#DPHelmbold|David P. Helmbold]], [[Mathematician#DHHaussler|David Haussler]], [[Robert Schapire]], [[Mathematician#MKWarmuth|Manfred K. Warmuth]] ('''1997'''). ''How to Use Expert Advice''. [[ACM#Journal|Journal of the ACM]], Vol. 44, No. 3, [http://homes.di.unimi.it/cesa-bianchi/Pubblicazioni/jacm-97a.pdf pdf]
* [[Peter Auer]], [[Nicolò Cesa-Bianchi]], [[Yoav Freund]], [[Robert Schapire]] ('''1998'''). ''Gambling in a rigged casino: The adversarial multi-arm bandit problem''. [http://www.bio.net/bioarchives/neuroscience/1998-November/034748.html NeuroCOLT2], [http://www.dklevine.com/archive/refs4462.pdf pdf]
* [[Nicolò Cesa-Bianchi]], [[Paul Fischer]] ('''1998'''). ''Finite-Time Regret Bounds for the Multiarmed Bandit Problem''. [http://dblp.uni-trier.de/db/conf/icml/icml1998.html#Cesa-BianchiF98 ICML 1998], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.57.4710 CiteSeerX]
==2000 ...==
* [[Peter Auer]], [[Nicolò Cesa-Bianchi]], [[Yoav Freund]], [[Robert Schapire]] ('''2002'''). ''The Nonstochastic Multiarmed Bandit Problem''. [https://en.wikipedia.org/wiki/SIAM_Journal_on_Computing SIAM Journal on Computing], Vol. 32, No. 1, [http://cseweb.ucsd.edu/~yfreund/papers/bandits.pdf 2001 pdf]
* [[Peter Auer]], [[Nicolò Cesa-Bianchi]], [[Paul Fischer]] ('''2002'''). ''[http://link.springer.com/article/10.1023%2FA%3A1013689704352 Finite-time Analysis of the Multiarmed Bandit Problem]''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 47, No. 2, [http://homes.di.unimi.it/~cesabian/Pubblicazioni/ml-02.pdf pdf]
* [[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2003'''). ''Potential-based Algorithms in On-line Prediction and Game Theory''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 51, [http://www.econ.upf.edu/~lugosi/potential.pdf pdf]
* [[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2006'''). ''[http://homes.di.unimi.it/cesa-bianchi/predbook/ Prediction, Learning, and Games]''. [https://en.wikipedia.org/wiki/Cambridge_University_Press Cambridge University Press]
* [[Nicolò Cesa-Bianchi]] ('''2009'''). ''Online discriminative learning: theory and applications''. [http://dblp.uni-trier.de/db/conf/asru/asru2009.html#Cesa-Bianchi09 ASRU 2009]
==2010 ...==
* [http://dblp.uni-trier.de/pers/hd/v/Vitale:Fabio Fabio Vitale], [[Nicolò Cesa-Bianchi]], [http://dblp.uni-trier.de/pers/hd/g/Gentile:Claudio Claudio Gentile], [http://giovannizappella.com/ Giovanni Zappella] ('''2011'''). ''See the Tree Through the Lines: The Shazoo Algorithm''. [http://dblp.uni-trier.de/db/conf/nips/nips2011.html#VitaleCGZ11 NIPS 2011], [http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2011_0908.pdf pdf]
* [[Nicolò Cesa-Bianchi]] ('''2011'''). ''The Game-Theoretic Approach to Machine Learning and Adaptation''. [http://dblp.uni-trier.de/db/conf/icais/icais2011.html#Cesa-Bianchi11 ICAIS 2011]
* [[Nicolò Cesa-Bianchi]] ('''2011'''). ''Ensembles and Multiple Classifiers: A Game-Theoretic View''. [http://dblp.uni-trier.de/db/conf/mcs/mcs2011.html#Cesa-Bianchi11 MCS 2011]
* [[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2012'''). ''Combinatorial Bandits''. [http://www.journals.elsevier.com/journal-of-computer-and-system-sciences/ Journal of Computer and System Sciences], Vol. 78, [http://www.econ.upf.edu/~lugosi/comband.pdf preprint as pdf]
* [[Sébastien Bubeck]], [[Nicolò Cesa-Bianchi]] ('''2012'''). ''Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems''. [http://dblp.uni-trier.de/db/journals/ftml/ftml5.html Foundations and Trends in Machine Learning, Vol. 5], No. 1, [http://www.princeton.edu/~sbubeck/SurveyBCB12.pdf pdf]
* [[Sébastien Bubeck]], [[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2013'''). ''Bandits With Heavy Tail''. [[IEEE#TIT|IEEE Transactions on Information Theory]], Vol. 59, No. 11, [http://arxiv.org/abs/1209.1727v1 arXiv:1209.1727v1]
* [[Nicolò Cesa-Bianchi]] ('''2015'''). ''[http://link.springer.com/referenceworkentry/10.1007/978-3-642-27848-8_768-1 Multi-armed Bandit Problem]''. [http://link.springer.com/book/10.1007/978-3-642-27848-8 Encyclopedia of Algorithms 2015]
=External Links=
* [http://homes.di.unimi.it/cesa-bianchi/ Nicolò Cesa-Bianchi]
* [https://en.wikipedia.org/wiki/Nicol%C3%B2_Cesa-Bianchi Nicolò Cesa-Bianchi from Wikipedia]
* [https://scholar.google.com/citations?user=BWADJUkAAAAJ&hl=en Nicolò Cesa-Bianchi - Google Scholar Citations]
* [http://videolectures.net/nicolo_cesa_bianchi/ Nicolò Cesa-Bianchi - University of Milan - VideoLectures.NET]
=References=
<references />
'''[[People|Up one Level]]'''
[[FILE:nicolocesabianchi.jpg|border|right|thumb|link=https://scholar.google.com/citations?user=BWADJUkAAAAJ&hl=en| Nicolò Cesa-Bianchi <ref>[https://scholar.google.com/citations?user=BWADJUkAAAAJ&hl=en Nicolò Cesa-Bianchi - Google Scholar Citations]</ref> ]]
'''Nicolò Cesa-Bianchi''',<br/>
an Italian computer scientist and professor at department of computer science, [https://en.wikipedia.org/wiki/University_of_Milan University of Milan]. His research interests include a wide range in the fields of [[Learning|machine learning]] and [https://en.wikipedia.org/wiki/Computational_learning_theory computational learning theory], such as [[Reinforcement Learning|reinforcement learning]], [https://en.wikipedia.org/wiki/Game_theory game-theoretic] learning, [https://en.wikipedia.org/wiki/Statistical_learning_theory statistical learning theory], [https://en.wikipedia.org/wiki/Prediction prediction] with expert advice, and [https://en.wikipedia.org/wiki/Multi-armed_bandit bandit problems]. Along with [[Gábor Lugosi]], he authored ''Prediction, Learning, and Games'' in 2006 <ref>[[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2006'''). ''[http://homes.di.unimi.it/cesa-bianchi/predbook/ Prediction, Learning, and Games]''. [https://en.wikipedia.org/wiki/Cambridge_University_Press Cambridge University Press]
"...beware of mathematicians, and all those who make empty prophecies. The danger already exists that the mathematicians have made a covenant with the devil to darken the spirit and to confine man in the bonds of Hell". [https://en.wikipedia.org/wiki/Augustine_of_Hippo St. Augustine], [http://www.augustinus.it/latino/genesi_lettera/genesi_lettera_02.htm De Genesi ad Litteram libri duodecim. Liber Secundus, 17, 37.]</ref>.
=Bandit Problems=
In [https://en.wikipedia.org/wiki/Probability_theory probability theory], the [https://en.wikipedia.org/wiki/Multi-armed_bandit multi-armed bandit problem] faces the tradeoff between [https://en.wikipedia.org/wiki/Exploitation_%28disambiguation%29 exploitation] of the [https://en.wikipedia.org/wiki/Slot_machine slot machine] that has the highest expected payoff and [https://en.wikipedia.org/wiki/Exploration exploration] to get more information about the expected payoffs of the other machines. The trade-off between exploration and exploitation is also topic in [[Reinforcement Learning|reinforcement learning]] <ref>[https://en.wikipedia.org/wiki/Multi-armed_bandit Multi-armed bandit from Wikipedia]</ref>. The [https://en.wikipedia.org/wiki/Gambling gambler] has to decide at time steps t = 1, 2, ... which of the finitely many available arms to pull. Each arm produces a [https://en.wikipedia.org/wiki/Reward reward] in a [https://en.wikipedia.org/wiki/Stochastic stochastic] manner. The goal is to maximize the reward accumulated over time. In 2002, along with [[Peter Auer]] and [[Paul Fischer]], Nicolò Cesa-Bianchi introduced the '''UCB1''' (Upper Confidence Bounds) bandit algorithm <ref>[[Peter Auer]], [[Nicolò Cesa-Bianchi]], [[Paul Fischer]] ('''2002'''). ''[http://link.springer.com/article/10.1023%2FA%3A1013689704352 Finite-time Analysis of the Multiarmed Bandit Problem]''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 47, No. 2, [http://homes.di.unimi.it/~cesabian/Pubblicazioni/ml-02.pdf pdf]</ref>, which was applied as selection algorithm [[UCT]] to [[Monte-Carlo Tree Search]] as elaborated by [[Levente Kocsis]] and [[Csaba Szepesvári]] in 2006 <ref>[[Levente Kocsis]], [[Csaba Szepesvári]] ('''2006'''). ''[http://www.computer-go.info/resources/bandit.html Bandit based Monte-Carlo Planning]'' ECML-06, LNCS/LNAI 4212, [http://www.sztaki.hu/%7Eszcsaba/papers/ecml06.pdf pdf]</ref>.
=Selected Publications=
<ref>[http://dblp.uni-trier.de/pers/hd/c/Cesa=Bianchi:Nicol=ograve= dblp: Nicolò Cesa-Bianchi]</ref> <ref>[http://homes.di.unimi.it/cesa-bianchi/papers.html Nicolò Cesa-Bianchi - Selected papers:]</ref>
==1990 ...==
* [[Nicolò Cesa-Bianchi]] ('''1990'''). ''Learning the Distribution in the Extended PAC Model''. [http://dblp.uni-trier.de/db/conf/alt/alt1990.html#Cesa-Bianchi90 ALT 1990]
* [[Peter Auer]], [[Nicolò Cesa-Bianchi]] ('''1994'''). ''On-line learning with malicious noise and the closure algorithm''. [http://www.springer.com/gp/book/9783540585206 Algorithmic Learning Theory], [https://en.wikipedia.org/wiki/Lecture_Notes_in_Computer_Science LNAI], [https://en.wikipedia.org/wiki/Springer_Science%2BBusiness_Media Springer]
* [[Nicolò Cesa-Bianchi]], [[Yoav Freund]], [[Mathematician#DPHelmbold|David P. Helmbold]], [[Mathematician#MKWarmuth|Manfred K. Warmuth]] ('''1996'''). ''On-line Prediction and Conversion Strategies''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 25, No 1, [http://homes.di.unimi.it/cesa-bianchi/Pubblicazioni/ml-96.pdf pdf]
* [[Nicolò Cesa-Bianchi]], [[Yoav Freund]], [[Mathematician#DPHelmbold|David P. Helmbold]], [[Mathematician#DHHaussler|David Haussler]], [[Robert Schapire]], [[Mathematician#MKWarmuth|Manfred K. Warmuth]] ('''1997'''). ''How to Use Expert Advice''. [[ACM#Journal|Journal of the ACM]], Vol. 44, No. 3, [http://homes.di.unimi.it/cesa-bianchi/Pubblicazioni/jacm-97a.pdf pdf]
* [[Peter Auer]], [[Nicolò Cesa-Bianchi]], [[Yoav Freund]], [[Robert Schapire]] ('''1998'''). ''Gambling in a rigged casino: The adversarial multi-arm bandit problem''. [http://www.bio.net/bioarchives/neuroscience/1998-November/034748.html NeuroCOLT2], [http://www.dklevine.com/archive/refs4462.pdf pdf]
* [[Nicolò Cesa-Bianchi]], [[Paul Fischer]] ('''1998'''). ''Finite-Time Regret Bounds for the Multiarmed Bandit Problem''. [http://dblp.uni-trier.de/db/conf/icml/icml1998.html#Cesa-BianchiF98 ICML 1998], [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.57.4710 CiteSeerX]
==2000 ...==
* [[Peter Auer]], [[Nicolò Cesa-Bianchi]], [[Yoav Freund]], [[Robert Schapire]] ('''2002'''). ''The Nonstochastic Multiarmed Bandit Problem''. [https://en.wikipedia.org/wiki/SIAM_Journal_on_Computing SIAM Journal on Computing], Vol. 32, No. 1, [http://cseweb.ucsd.edu/~yfreund/papers/bandits.pdf 2001 pdf]
* [[Peter Auer]], [[Nicolò Cesa-Bianchi]], [[Paul Fischer]] ('''2002'''). ''[http://link.springer.com/article/10.1023%2FA%3A1013689704352 Finite-time Analysis of the Multiarmed Bandit Problem]''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 47, No. 2, [http://homes.di.unimi.it/~cesabian/Pubblicazioni/ml-02.pdf pdf]
* [[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2003'''). ''Potential-based Algorithms in On-line Prediction and Game Theory''. [https://en.wikipedia.org/wiki/Machine_Learning_%28journal%29 Machine Learning], Vol. 51, [http://www.econ.upf.edu/~lugosi/potential.pdf pdf]
* [[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2006'''). ''[http://homes.di.unimi.it/cesa-bianchi/predbook/ Prediction, Learning, and Games]''. [https://en.wikipedia.org/wiki/Cambridge_University_Press Cambridge University Press]
* [[Nicolò Cesa-Bianchi]] ('''2009'''). ''Online discriminative learning: theory and applications''. [http://dblp.uni-trier.de/db/conf/asru/asru2009.html#Cesa-Bianchi09 ASRU 2009]
==2010 ...==
* [http://dblp.uni-trier.de/pers/hd/v/Vitale:Fabio Fabio Vitale], [[Nicolò Cesa-Bianchi]], [http://dblp.uni-trier.de/pers/hd/g/Gentile:Claudio Claudio Gentile], [http://giovannizappella.com/ Giovanni Zappella] ('''2011'''). ''See the Tree Through the Lines: The Shazoo Algorithm''. [http://dblp.uni-trier.de/db/conf/nips/nips2011.html#VitaleCGZ11 NIPS 2011], [http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2011_0908.pdf pdf]
* [[Nicolò Cesa-Bianchi]] ('''2011'''). ''The Game-Theoretic Approach to Machine Learning and Adaptation''. [http://dblp.uni-trier.de/db/conf/icais/icais2011.html#Cesa-Bianchi11 ICAIS 2011]
* [[Nicolò Cesa-Bianchi]] ('''2011'''). ''Ensembles and Multiple Classifiers: A Game-Theoretic View''. [http://dblp.uni-trier.de/db/conf/mcs/mcs2011.html#Cesa-Bianchi11 MCS 2011]
* [[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2012'''). ''Combinatorial Bandits''. [http://www.journals.elsevier.com/journal-of-computer-and-system-sciences/ Journal of Computer and System Sciences], Vol. 78, [http://www.econ.upf.edu/~lugosi/comband.pdf preprint as pdf]
* [[Sébastien Bubeck]], [[Nicolò Cesa-Bianchi]] ('''2012'''). ''Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems''. [http://dblp.uni-trier.de/db/journals/ftml/ftml5.html Foundations and Trends in Machine Learning, Vol. 5], No. 1, [http://www.princeton.edu/~sbubeck/SurveyBCB12.pdf pdf]
* [[Sébastien Bubeck]], [[Nicolò Cesa-Bianchi]], [[Gábor Lugosi]] ('''2013'''). ''Bandits With Heavy Tail''. [[IEEE#TIT|IEEE Transactions on Information Theory]], Vol. 59, No. 11, [http://arxiv.org/abs/1209.1727v1 arXiv:1209.1727v1]
* [[Nicolò Cesa-Bianchi]] ('''2015'''). ''[http://link.springer.com/referenceworkentry/10.1007/978-3-642-27848-8_768-1 Multi-armed Bandit Problem]''. [http://link.springer.com/book/10.1007/978-3-642-27848-8 Encyclopedia of Algorithms 2015]
=External Links=
* [http://homes.di.unimi.it/cesa-bianchi/ Nicolò Cesa-Bianchi]
* [https://en.wikipedia.org/wiki/Nicol%C3%B2_Cesa-Bianchi Nicolò Cesa-Bianchi from Wikipedia]
* [https://scholar.google.com/citations?user=BWADJUkAAAAJ&hl=en Nicolò Cesa-Bianchi - Google Scholar Citations]
* [http://videolectures.net/nicolo_cesa_bianchi/ Nicolò Cesa-Bianchi - University of Milan - VideoLectures.NET]
=References=
<references />
'''[[People|Up one Level]]'''
