Distributionally Robust Counterfactual Risk Minimization
نویسندگان
چکیده
منابع مشابه
Counterfactual Risk Minimization
We develop a learning principle and an efficient algorithm for batch learning from logged bandit feedback. Unlike in supervised learning, where the algorithm receives training examples (xi, y ∗ i ) with annotated correct labels y ∗ i , bandit feedback merely provides a cardinal reward δi ∈ R for the prediction yi that the logging system made for context xi. Such bandit feedback is ubiquitous in...
متن کاملDistributionally Robust Games with Risk-averse Players
We present a new model of incomplete information games without private information in which the players use a distributionally robust optimization approach to cope with the payoff uncertainty. With some specific restrictions, we show that our “Distributionally Robust Game” constitutes a true generalization of three popular finite games. These are the Complete Information Games, Bayesian Games a...
متن کاملDistributionally Robust Stochastic Programming
Abstract. In this paper we study distributionally robust stochastic programming in a setting 7 where there is a specified reference probability measure and the uncertainty set of probability mea8 sures consists of measures in some sense close to the reference measure. We discuss law invariance of 9 the associated worst case functional and consider two basic constructions of such uncertainty set...
متن کاملDistributionally Robust Logistic Regression
This paper proposes a distributionally robust approach to logistic regression. We use the Wasserstein distance to construct a ball in the space of probability distributions centered at the uniform distribution on the training samples. If the radius of this ball is chosen judiciously, we can guarantee that it contains the unknown datagenerating distribution with high confidence. We then formulat...
متن کاملDistributionally Robust Submodular Maximization
Submodular functions have applications throughout machine learning, but in many settings, we do not have direct access to the underlying function f . We focus on stochastic functions that are given as an expectation of functions over a distribution P . In practice, we often have only a limited set of samples fi from P . The standard approach indirectly optimizes f by maximizing the sum of fi. H...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i04.5797