Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families
نویسندگان
چکیده
We study online learning under logarithmic loss with regular parametric models. Hedayati and Bartlett (2012b) showed that a Bayesian prediction strategy with Jeffreys prior and sequential normalized maximum likelihood (SNML) coincide and are optimal if and only if the latter is exchangeable, and if and only if the optimal strategy can be calculated without knowing the time horizon in advance. They put forward the question what families have exchangeable SNML strategies. This paper fully answers this open problem for onedimensional exponential families. The exchangeability can happen only for three classes of natural exponential family distributions, namely the Gaussian, Gamma, and the Tweedie exponential family of order 3/2.
منابع مشابه
Bayes, E-Bayes and Robust Bayes Premium Estimation and Prediction under the Squared Log Error Loss Function
In risk analysis based on Bayesian framework, premium calculation requires specification of a prior distribution for the risk parameter in the heterogeneous portfolio. When the prior knowledge is vague, the E-Bayesian and robust Bayesian analysis can be used to handle the uncertainty in specifying the prior distribution by considering a class of priors instead of a single prior. In th...
متن کاملHorizon-Independent Optimal Pricing in Repeated Auctions with Truthful and Strategic Buyers
We study revenue optimization learning algorithms for repeated posted-price auctions where a seller interacts with a (truthful or strategic) buyer that holds a fixed valuation. We focus on a practical situation in which the seller does not know in advance the number of played rounds (the time horizon) and has thus to use a horizon-independent pricing. First, we consider straightforward modifica...
متن کاملFuture record values prediction in exponential distribution
According to the first nth observations of the upper record from exponential distribution, in this article, we can compute maximum likelihood estimation of this distribution parameter. We, then, concentrate on point prediction of the future upper record values in exponential distribution based both on classic and Bayes approaches and second degree and linex loss functions.We, ultimately, de...
متن کاملA Hierarchical Production Planning and Finite Scheduling Framework for Part Families in Flexible Job-shop (with a case study)
Tendency to optimization in last decades has resulted in creating multi-product manufacturing systems. Production planning in such systems is difficult, because optimal production volume that is calculated must be consistent with limitation of production system. Hence, integration has been proposed to decide about these problems concurrently. Main problem in integration is how we can relate pro...
متن کاملSoft-Bayes: Prod for Mixtures of Experts with Log-Loss
We consider prediction with expert advice under the log-loss with the goal of deriving efficient and robust algorithms. We argue that existing algorithms such as exponentiated gradient, online gradient descent and online Newton step do not adequately satisfy both requirements. Our main contribution is an analysis of the Prod algorithm that is robust to any data sequence and runs in linear time ...
متن کامل