Search Results for author: Alexander Zimin

Found 4 papers, 0 papers with code

MACRO: A Meta-Algorithm for Conditional Risk Minimization

no code implementations1 Jan 2018 Alexander Zimin, Christoph Lampert

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

Conditional Risk Minimization for Stochastic Processes

no code implementations9 Oct 2015 Alexander Zimin, Christoph H. Lampert

In particular, we aim at learning predictors that minimize the conditional risk for a stochastic process, i. e. the expected loss of the predictor on the next point conditioned on the set of training samples observed so far.

Time Series Time Series Prediction

Generalized Risk-Aversion in Stochastic Multi-Armed Bandits

no code implementations5 May 2014 Alexander Zimin, Rasmus Ibsen-Jensen, Krishnendu Chatterjee

We consider the problem of minimizing the regret in stochastic multi-armed bandit, when the measure of goodness of an arm is not the mean return, but some general function of the mean and the variance. We characterize the conditions under which learning is possible and present examples for which no natural algorithm can achieve sublinear regret.

Multi-Armed Bandits

Online learning in episodic Markovian decision processes by relative entropy policy search

no code implementations NeurIPS 2013 Alexander Zimin, Gergely Neu

We study the problem of online learning in finite episodic Markov decision processes where the loss function is allowed to change between episodes.

online learning

Cannot find the paper you are looking for? You can Submit a new open access paper.