|
|
L. Addario-Berry,
N. Broutin,
and G. Lugosi
(2009).
Effective resistance of random trees.
Annals of Applied Probability, 19:1092-1107.
(PDF)
|
|
L. Devroye,
G. Lugosi, and
G. Park, and
W. Szpankowski
(2009).
Multiple choice tries.
Random Structures and Algorithms, 34:337-367.
(PDF)
(An earlier version appeared in
the Proceedings of the
SIAM-ACM Symposium on Discrete Algorithms (SODA 2007). (PDF)
|
|
|
G. Lugosi,
S. Mannor,
and
G. Stoltz
(2008).
Strategies for prediction under imperfect monitoring.
Mathematics of Operations Research, 33:513--528.
(PDF)
|
|
|
G. Biau,
L. Devroye,
and G. Lugosi
(2008).
Consistency of random forests and other averaging classifiers.
Journal of Machine Learning Research, 9:2015--2033, 2008.
(PDF)
|
|
|
S. Clémençon,
G. Lugosi, and
N. Vayatis
(2008).
Ranking and empirical minimization of U-statistics.
Annals of Statistics,
36:844--874.
(PDF)
An earlier version
appeared at COLT 2005
(PDF, PS).
My coauthors in 1974 just before
the casting of a John Holmes movie. (None of them got the part.)
|
|
|
A. György,
T. Linder,
and G. Lugosi (2008).
Tracking the best quantizer.
IEEE Transactions on Information Theory,
54:1604--1625.
(PDF)
(Some parts of this paper are based on
``Tracking the best of many experts.''
(PDF, PS)
Proceedings of the
18th Annual Conference on
Learning Theory, Springer, pp. 204--216, 2005.)
|
|
|
L. Devroye and
G. Lugosi (2008).
Local tail bounds for functions of independent random variables.
The Annals of Probability, 36:143--159.
(PDF, PS)
|
|
|
G. Biau,
L. Devroye and
G. Lugosi (2008).
On the performance of clustering in Hilbert spaces.
IEEE Transactions on Information Theory,
54:781--790.
(PDF)
|
|
|
A. György,
T. Linder,
G. Lugosi,
and
Gy. Ottucsák,
(2007).
The on-line shortest path problem under partial monitoring.
Journal of Machine Learning Research, 8:2369--2403.
(PDF)
|
|
|
F. Germano
and G. Lugosi (2007).
Global Nash convergence of Foster and Young's regret testing.
Games and Economic Behavior,
60:135-154.
(PDF,POSTSCRIPT)
|
|
|
F. Germano
and G. Lugosi (2007).
Existence of sparsely supported correlated
equilibria.
Economic Theory, 32:575--578.
(PDF,POSTSCRIPT)
|
|
|
G. Stoltz
and G. Lugosi,
(2007).
Learning correlated equilibria in games with compact sets of strategies.
Games and Economic Behavior, 59:187-208.
(PDF)
|
|
|
G. Lugosi (2006).
Prédiction randomisée de suites individuelles.
Journal de la Société Française de
Statistique, 147:5-37.
(PDF)
|
|
|
S. Clemençon,
G. Lugosi, and
N. Vayatis
(2006).
Some comments on "Local Rademacher complexities and oracle inequalities in
risk minimization" by Vladimir Koltchinskii.
Annals of Statistics,
34:2672--2676.
(PDF)
|
|
|
N. Cesa-Bianchi,
G. Lugosi, and
G. Stoltz
(2006).
Regret minimization under partial monitoring.
Mathematics of Operations Research, 31:562--580.
(PDF,POSTSCRIPT)
|
|
|
L. Györfi,
G. Lugosi, and
F. Udina
(2006).
Nonparametric kernel-based sequential investment strategies.
Mathematical Finance, 16:337--358.
(PDF),
(POSTSCRIPT)
|
|
S. Boucheron,
O. Bousquet, and
G. Lugosi, (2005).
Theory of Classification: a Survey of Recent Advances.
ESAIM: Probability and Statistics, 9:323-375.
(PDF,POSTSCRIPT)
|
|
R. Cao
and G. Lugosi,
(2005).
Goodness-of-fit tests based on the kernel density estimate.
Scandinavian Journal of Statistics, 32:599-617.
(PDF)
|
|
N. Cesa-Bianchi,
G. Lugosi, and
G. Stoltz
(2005).
Minimizing regret with label efficient prediction.
IEEE Transactions on Information Theory, 51:2152--2162.
(PDF,POSTSCRIPT)
|
|
S. Boucheron,
O. Bousquet,
G. Lugosi, and
P. Massart (2005).
Moment inequalities for functions of independent random variables.
The Annals of Probability, 33:514--560.
(PDF,POSTSCRIPT)
|
|
G. Stoltz
and G. Lugosi (2005).
"Internal regret in on-line portfolio selection."
Machine Learning, 59:125-159.
(POSTSCRIPT)
|
|
A. György,
T. Linder,
and G. Lugosi (2004).
"Efficient Algorithms and Minimax Bounds for Zero-Delay Lossy
Source Coding."
IEEE Transactions on Signal Processing, vol.52, pp.2337--2347.
(PDF),
(POSTSCRIPT)
A related result published in
DCC
is here: PDF,
POSTSCRIPT
|
|
L. Devroye
and G. Lugosi,
(2004).
"Bin width selection in multivariate histograms by the combinatorial
method."
Test,
vol.13, pp.1--17 (PDF,POSTSCRIPT)
|
|
|
G. Lugosi and
M. Wegkamp (2004).
"Complexity regularization via localized random penalties."
Annals of Statistics,
vol.32, no.4.
(PDF,POSTSCRIPT)
|
|
G. Lugosi and
N. Vayatis
(2004).
"On the Bayes-risk consistency of regularized boosting methods."
Annals of Statistics,
vol.32, pp.30--55.
(PDF,POSTSCRIPT)
with discussion.
|
|
|
G. Lugosi, S. Mendelson,
and V. Koltchinskii
(2003).
"A note on the richness of convex hulls of VC classes."
Electronic Communications in Probability, 8:167--169.
(PDF,POSTSCRIPT)
|
|
G. Blanchard,
G. Lugosi, and
N. Vayatis
(2003).
"On the rate of convergence of regularized boosting classifiers."
Journal of Machine Learning Research,
4:861-894.
(PDF,POSTSCRIPT)
|
|
S. Boucheron,
G. Lugosi, and
P. Massart (2003).
"Concentration inequalities using the entropy method."
The Annals of Probability, , vol 31:1583-1614.
(PDF,POSTSCRIPT)
|
|
|
N. Cesa-Bianchi
and G. Lugosi (2003).
"Potential-based algorithms in on-line prediction and
game theory."
Machine Learning,
vol.51, pp. 239--261.
(PDF,POSTSCRIPT)
|
|
|
A. Antos,
B. Kégl,
T.
Linder and G. Lugosi (2002).
"Data-dependent margin-based generalization bounds for
classification."
Journal of Machine Learning Research, vol. 3, pp.73--98.
(PDF,POSTSCRIPT)
|
|
|
L. Devroye and
G. Lugosi, (2002). "Almost sure
classification of densities."
Journal of Nonparametric Statistics, vol. 14, pp.675--698.
(PDF,POSTSCRIPT)
|
|
|
L. Devroye,
L. Györfi, and
G. Lugosi, (2002). "A note on
robust hypothesis testing."
IEEE Transactions on Information Theory, , vol. 48, pp.2111--2114.
|
|
|
P. Bartlett,
S. Boucheron,
and G. Lugosi (2002).
"Model selection and error estimation."
Machine Learning.
vol.48, pp. 85-113
|
|
|
T.
Linder and G. Lugosi (2001).
"A Zero-Delay Sequential Scheme
for Lossy Coding of Individual Sequences".
IEEE Transactions on Information Theory, , 47:2533--2538.
|
|
|
L. Györfi, and G. Lugosi (2001).
"Strategies for sequential prediction of stationary
time series".
in Moshe Dror, Pierre L'Ecuyer, Ferenc Szidarovszky (editors),
Modeling Uncertainty:An examination of its theory, methods, and
applications.,
Kluwer Academic Publishers
|
|
|
N. Cesa-Bianchi
and G. Lugosi (2001).
"Worst-case bounds for the logarithmic loss of predictors."
Machine Learning
vol.43(3). pp.247--264.
|
|
|
S. Boucheron,
G. Lugosi, and
P. Massart (2000).
"A sharp concentration inequality with applications."
Random Structures and Algorithms vol.16, pp.277-292.
|
|
|
S. Kulkarni
and G. Lugosi (2000). "Minimax lower bounds for
the two-armed bandit problem."
IEEE Transactions on Automatic Control. vol.45, pp.711-714.
|
|
|
L. Devroye, G. Lugosi,
and F. Udina (2000). "Inequalities
for a new data-based method for selecting nonparametric density estimates"
in M.L. Puri (editor),
Asymptotics in Statistics and Probability.
Papers in Honor of George Gregory Roussas.,
VSP International Science Publishers, The Netherlands, 2000.
|
|
|
L. Devroye and
G. Lugosi, (2000). "Variable kernel estimates:
on the impossibility of tuning the parameters."
in: E. Giné, D. Mason, and J. Wellner (editors),
High-Dimensional Probability II,
Springer-Verlag,
New York,
2000
|
|
|
N. Cesa-Bianchi
and G. Lugosi (1999).
"On prediction of individual sequences."
Annals of Statistics
vol. 27, 1865--1895.
|
|
|
G. Lugosi and A. Nobel (1999).
"Adaptive Model Selection Using Empirical Complexities."
Annals of Statistics
vol. 27(6), 1830-1864.
|
|
|
L. Györfi, G. Lugosi and G. Morvai (1999). "A
simple randomized algorithm for consistent sequential prediction of ergodic
time series"
IEEE Transactions on Information Theory, vol.45, 2642--2650.
|
|
|
P. Bartlett and G.
Lugosi (1999). "An inequality for uniform deviations
of sample averages from their means"
Statistics and Probability Letters, vol.44, 55--62.
|
|
|
S. Kulkarni,
G. Lugosi, and S. Venkatesh (1998).
"Learning Pattern Classification---A Survey."
1948--1998 Special Commemorative Issue of
IEEE Transactions on Information Theory. , vol.44, 2178--2206.
Reprinted in S. Verdú, S.W. McLaughlin (editors.),
Information Theory: 50 Years of Discovery,
IEEE Press, New York, 1999.
| 
|
|
|
A. Antos, G. Lugosi (1998).
"Strong minimax lower bounds for learning,"
Machine Learning,
vol.30, 31--56.
|
|
|
P. Bartlett, T.
Linder, and G. Lugosi (1998). The minimax distortion redundancy
in empirical quantizer design.
IEEE Transactions on Information Theory. , vol. 44, 1802--1813.
|
|
|
M. Horváth, G. Lugosi (1998). "A data-dependent skeleton
estimate and a scale-sensitive dimension for classification."
Discrete Applied Mathematics, Special issue on the Vapnik-Chervonenkis
dimension. vol. 86, no. 1, pp. 37-61.
|
|
|
L. Devroye, G. Lugosi
(1997). "Nonasymptotic smoothing factors, kernel complexity, and Yatracos
classes."
Annals of Statistics
, vol. 25.,2626--2635.
|
|
|
G. Lugosi (1997).
Comments to "Universal smoothing factor selection
in density estimation: theory and practice" by Luc Devroye.
Test, vol. 6, pp. 291--296.
|
|
|
T. Linder, G. Lugosi,
and K. Zeger (1997). "Empirical
Quantizer Design in the Presence of Source Noise or Channel Noise",
IEEE Transactions on Information Theory. , vol. 43, no. 2, pp. 612--623, March.
|
|
|
L. Devroye, G. Lugosi
(1996). "A universally acceptable smoothing factor for kernel density
estimates,"
Annals of Statistics
, vol.24, pp.2499--2512.
|
|
|
G. Lugosi, K. Zeger
(1996). "Concept learning using complexity regularization,"
IEEE Transactions on Information Theory. , vol.42, No.1, pp.48--54.
|
|
|
G. Lugosi, A. Nobel (1996). "Consistency of data-driven histogram
methods for density estimation and classification,"
Annals of Statistics
vol. 24, No.2, pp.687--706.
(PDF)
|
|
|
A.
Krzyzak, T. Linder,
and G. Lugosi (1996). "Nonparametric Estimation and Classification
using Radial Basis Function Nets and Empirical Risk Minimization,"
IEEE Transactions on Neural Networks, vol. 7, pp.475--487.
|
|
|
L. Devroye, G. Lugosi
(1995). "Lower bounds in pattern recognition and learning,"
Pattern Recognition, vol.28, No.7, pp.1011--1018.
|
|
|
G. Lugosi (1995). "Improved upper bounds for probabilities of uniform deviations,"
Statistics and Probability Letters, vol.25, pp.71--77.
|
|
|
G. Lugosi, K. Zeger
(1995). "Nonparametric estimation via empirical risk minimization,"
IEEE Transactions on Information Theory. , vol.41, No.3, pp.677--687.
|
|
|
T. Linder, T. Lugosi,
and K. Zeger (1995). "Fixed
Rate Universal Lossy Source Coding and Rates of Convergence for Memoryless
Sources",
IEEE Transactions on Information Theory. , vol. 41, no. 3,
pp. 665-676.
|
|
|
T. Linder, T. Lugosi,
and K. Zeger (1994). "Rates
of Convergence in the Source Coding Theorem, in Empirical Quantizer Design,
and in Universal Lossy Source Coding",
IEEE Transactions on Information Theory. , vol. 40, no. 6, pp. 1728-1740.
(PDF)
|
|
|
J. Beirlant, L. Györfi, G. Lugosi (1994). "On the asymptotic normality
of the $L_1$- and $L_2$-errors in histogram density estimation,"
Canadian
Journal of Statistics, vol.22, No.3, pp.309--318.
|
|
|
L. Devroye,
L. Györfi,
A. Krzyzak,
G. Lugosi (1994). "On the strong universal consistency of nearest neighbor
regression function estimates,"
Annals of Statistics
, vol.22,
No.3, pp.1371--1385.
|
|
|
G. Lugosi,
M. Pawlak (1994). "On the posterior-probability estimate
of the error rate of nonparametric classification rules,"
IEEE Transactions on Information Theory. , vol.40, No.3, pp.475--481.
|
|
|
T. Linder, T. Lugosi,
and K. Zeger (1994). "Recent
Trends in Lossy Source Coding", Journal on Communications (Hungary),
vol. XLV, pp. 16-22.
|
|
|
A. Faragó,
T. Linder,
and G. Lugosi (1993). "Fast nearest neighbor search in dissimilarity
spaces" IEEE Transactions on Pattern Analysis and Machine Intelligence
vol. 18, no. 9, pp. 957-962.
(PDF)
|
|
|
A. Faragó,
G. Lugosi (1993). "Strong universal consistency
of neural network classifiers,"
IEEE Transactions on Information Theory. , vol.39, No.4, pp.1146--1151.
|
|
|
G. Lugosi (1992). "Learning with an unreliable teacher,"
Pattern Recognition, vol. 25 No. 1, pp.79-88.
|
|
|
L. Györfi, G. Lugosi (1992). "Kernel density estimation from ergodic
sample is not universally consistent,"
Computational Statistics and Data Analysis, vol.14, pp.437-442.
|
|
|
G. Lugosi (1991). "Pattern classification from distorted sample,"
Problems of Control and Information Theory vol.20, No.6, pp.465-473.
|
|
|
A. Faragó,
T. Linder
and G. Lugosi (1991). "Nearest neighbor search and classification in
O(1) time," Problems of Control and Information Theory pp.
475-482, vol. 20. no 6.
|
|
|
A. Faragó,
G. Lugosi (1989). "An algorithm to find the global
opimum of hidden Markov model parameters," Problems of Control
and Information Theory, Vol.18(6), pp.435-444.
(PDF)
|
|
|
|
|
|
|
|
|
|
|
|
