We study the problem of online learning in finite episodic Markov decision processes (MDPs) where the loss function is allowed to change between episodes. The natural performance measure in thisâ€¦ (More)

We consider the problem of minimizing the regret in stochas-tic multi-armed bandit, when the measure of goodness of an arm is not the mean return, but some general function of the mean and theâ€¦ (More)

In this work we study the learnability of stochastic processes with respect to the conditional risk, i.e. the existence of a learning algorithm that improves its next-step performance with the amountâ€¦ (More)

We study the task of learning from non-i.i.d. data. In particular, we aim at learning predictors that minimize the conditional risk for a stochastic process, i.e. the expected loss of the predictorâ€¦ (More)

To characterize a complexity of some function class we use covering numbers and a sequential fat-shattering dimension. But before we could give those de nitions, we need to introduce a notion ofâ€¦ (More)

We consider the problem of bounding large deviations for non-i.i.d. random variables that are allowed to have arbitrary dependences. Previous works typically assumed a specific dependence structure,â€¦ (More)

We study conditional risk minimization (CRM), i.e. the problem of learning a hypothesis of minimal risk for prediction at the next step of a sequentially arriving dependent data. Despite it being aâ€¦ (More)

AIM
To analyze the errors and complications of surgical care in patients with the first episode of spontaneous pneumothorax at different hospitals.
MATERIAL AND METHODS
From 2005 to 2015 threeâ€¦ (More)