Add to ORKGInternational audienceWe present deviation bounds for self-normalized averages and applications to estimation with a random number of observations. The results rely on a peeling argument in exponential martingale techniques that represents an alternative to the method of mixture. The motivating examples of bandit problems and context tree estimation are detailed
International audienceWe propose several exponential inequalities for self-normalized martingales si...
We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual bandits with ...
International audience<p>We consider the problem of efficiently exploring the arms of a stochastic b...
International audienceWe present deviation bounds for self-normalized averages and applications to e...
We consider, in a generic streaming regression setting, the problem of building a confidence interva...
Context tree models have been introduced by Rissanen in [25] as a parsimonious generalization of Mar...
This paper presents new deviation inequalities that are valid uniformly in time under adaptive samp...
International audienceWe fill in a long open gap in the characterization of the minimax rate for the...
This paper is devoted to regret lower bounds in the classical model of stochastic multi-armed bandit...
AbstractContext tree models have been introduced by Rissanen in [25] as a parsimonious generalizatio...
International audienceAlgorithms based on upper-confidence bounds for balancing exploration and expl...
We provide a principled way of proving Omacr(radicT) high-probability guarantees for partial-informa...
Abstract: Self-normalized processes are basic to many probabilistic and statistical studies. They ar...
Cram\'er's moderate deviations give a quantitative estimate for the relative error of the normal app...
This paper is concerned with the information-theoretical limits of density estimation for Gaussian r...
International audienceWe propose several exponential inequalities for self-normalized martingales si...
We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual bandits with ...
International audience<p>We consider the problem of efficiently exploring the arms of a stochastic b...
International audienceWe present deviation bounds for self-normalized averages and applications to e...
We consider, in a generic streaming regression setting, the problem of building a confidence interva...
Context tree models have been introduced by Rissanen in [25] as a parsimonious generalization of Mar...
This paper presents new deviation inequalities that are valid uniformly in time under adaptive samp...
International audienceWe fill in a long open gap in the characterization of the minimax rate for the...
This paper is devoted to regret lower bounds in the classical model of stochastic multi-armed bandit...
AbstractContext tree models have been introduced by Rissanen in [25] as a parsimonious generalizatio...
International audienceAlgorithms based on upper-confidence bounds for balancing exploration and expl...
We provide a principled way of proving Omacr(radicT) high-probability guarantees for partial-informa...
Abstract: Self-normalized processes are basic to many probabilistic and statistical studies. They ar...
Cram\'er's moderate deviations give a quantitative estimate for the relative error of the normal app...
This paper is concerned with the information-theoretical limits of density estimation for Gaussian r...
International audienceWe propose several exponential inequalities for self-normalized martingales si...
We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual bandits with ...
International audience<p>We consider the problem of efficiently exploring the arms of a stochastic b...