Learning Theory for Conditional Risk Minimization
نویسندگان
چکیده
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 amount of observed data. We introduce a notion of pairwise discrepancy between conditional distributions at different times steps and show how certain properties of these discrepancies can be used to construct a successful learning algorithm. Our main results are two theorems that establish criteria for learnability for many classes of stochastic processes, including all special cases studied previously in the literature.
منابع مشابه
Portfolio Optimization Based on Cross Efficiencies By Linear Model of Conditional Value at Risk Minimization
Markowitz model is the first modern formulation of portfolio optimization problem. Relyingon historical return of stocks as basic information and using variance as a risk measure aretow drawbacks of this model. Since Markowitz model has been presented, many effortshave been done to remove theses drawbacks. On one hand several better risk measures havebeen introduced and proper models have been ...
متن کاملConditional Risk Minimization for Stochastic Processes
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 taking into account the set of training samples observed so far. For non-i.i.d. data, the training set contains information about the upcoming samples, so learning with respect to the conditional distribution can be ...
متن کاملRobust portfolio selection with polyhedral ambiguous inputs
Ambiguity in the inputs of the models is typical especially in portfolio selection problem where the true distribution of random variables is usually unknown. Here we use robust optimization approach to address the ambiguity in conditional-value-at-risk minimization model. We obtain explicit models of the robust conditional-value-at-risk minimization for polyhedral and correlated polyhedral am...
متن کاملNonparametric estimation via empirical risk minimization
A general notion of universal consistency of nonparametric estimators is introduced that applies to regression estimation, conditional median estimation, curve fitting, pattern recognition, and learning concepts. General methods for proving consistency of estimators based on minimizing the empirical error are shown. In particular, distribution-free almost sure consistency of neural network esti...
متن کاملTowards Practical Conditional Risk Minimization
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 a fundamental problem, successful learning in the CRM sense has so far only been demonstrated using theoretical algorithms that cannot be used for real problems as they would require storing all incomi...
متن کامل