top
We present a new and simple approach to some of the deviation inequalities
for product measures deeply investigated by M. Talagrand in the recent years.
Our method is based on functional inequalities of Poincaré and logarithmic
Sobolev type and iteration of these inequalities. In particular, we establish
with theses tools sharp deviation inequalities from the mean on norms of sums
of independent random vectors and empirical processes. Concentration for
the Hamming distance may also be deduced from this approach.
Ledoux, Michel. "On Talagrand's deviation inequalities for product measures." ESAIM: Probability and Statistics 1 (2010): 63-87. <http://eudml.org/doc/116580>.
@article{Ledoux2010, abstract = {
We present a new and simple approach to some of the deviation inequalities
for product measures deeply investigated by M. Talagrand in the recent years.
Our method is based on functional inequalities of Poincaré and logarithmic
Sobolev type and iteration of these inequalities. In particular, we establish
with theses tools sharp deviation inequalities from the mean on norms of sums
of independent random vectors and empirical processes. Concentration for
the Hamming distance may also be deduced from this approach.
}, author = {Ledoux, Michel}, journal = {ESAIM: Probability and Statistics}, keywords = {Concentration of measure / logarithmic Sobolev inequalities /
product measures / deviation inequalities / convex functions /
bounds on empirical processes.; deviation inequalities for product measures; functional inequalities; empirical processes; Hamming distance}, language = {eng}, month = {3}, pages = {63-87}, publisher = {EDP Sciences}, title = {On Talagrand's deviation inequalities for product measures}, url = {http://eudml.org/doc/116580}, volume = {1}, year = {2010}, }
TY - JOUR AU - Ledoux, Michel TI - On Talagrand's deviation inequalities for product measures JO - ESAIM: Probability and Statistics DA - 2010/3// PB - EDP Sciences VL - 1 SP - 63 EP - 87 AB -
We present a new and simple approach to some of the deviation inequalities
for product measures deeply investigated by M. Talagrand in the recent years.
Our method is based on functional inequalities of Poincaré and logarithmic
Sobolev type and iteration of these inequalities. In particular, we establish
with theses tools sharp deviation inequalities from the mean on norms of sums
of independent random vectors and empirical processes. Concentration for
the Hamming distance may also be deduced from this approach.
LA - eng KW - Concentration of measure / logarithmic Sobolev inequalities /
product measures / deviation inequalities / convex functions /
bounds on empirical processes.; deviation inequalities for product measures; functional inequalities; empirical processes; Hamming distance UR - http://eudml.org/doc/116580 ER -