Zobrazeno 1 - 10
of 84
pro vyhledávání: '"Harremoes, Peter"'
Information projections have found important applications in probability theory, statistics, and related areas. In the field of hypothesis testing in particular, the reverse information projection (RIPr) has recently been shown to lead to growth-rate
Externí odkaz:
http://arxiv.org/abs/2306.16646
Autor:
Harremoës, Peter
Information theory is built on probability measures and by definition a probability measure has total mass 1. Probability measures are used to model uncertainty, and one may ask how important it is that the total mass is one. We claim that the main r
Externí odkaz:
http://arxiv.org/abs/2202.02668
Autor:
Harremoës, Peter
Rate distortion theory was developed for optimizing lossy compression of data, but it also has a lot of applications in statistics. In this paper we will see how rate distortion theory can be used to analyze a complicated data set involving orientati
Externí odkaz:
http://arxiv.org/abs/2201.03707
Autor:
Harremoës, Peter, Matúš, František
The hypergeometric distributions have many important applications, but they have not had sufficient attention in information theory. Hypergeometric distributions can be approximated by binomial distributions or Poisson distributions. In this paper we
Externí odkaz:
http://arxiv.org/abs/2002.03002
Autor:
Harremoës, Peter
The principle called information causality has been used to deduce Tsirelson's bound. In this paper we derive information causality from monotonicity of divergence and relate it to more basic principles related to measurements on thermodynamic system
Externí odkaz:
http://arxiv.org/abs/2002.02895
Autor:
Harremoës, Peter
Statistical inference may follow a frequentist approach or it may follow a Bayesian approach or it may use the minimum description length principle (MDL). Our goal is to identify situations in which these different approaches to statistical inference
Externí odkaz:
http://arxiv.org/abs/1805.02234
Autor:
Harremoës, Peter
Recently it has been demonstrated that the Shannon entropy or the von Neuman entropy are the only entropy functions that generate a local Bregman divergences as long as the state space has rank 3 or higher. In this paper we will study the properties
Externí odkaz:
http://arxiv.org/abs/1707.03222
Autor:
Harremoës, Peter
For convex optimization problems Bregman divergences appear as regret functions. Such regret functions can be defined on any convex set but if a sufficiency condition is added the regret function must be proportional to information divergence and the
Externí odkaz:
http://arxiv.org/abs/1701.06688
Autor:
Harremoës, Peter
Logarithmic score and information divergence appear in information theory, statistics, statistical mechanics, and portfolio theory. We demonstrate that all these topics involve some kind of optimization that leads directly to regret functions and suc
Externí odkaz:
http://arxiv.org/abs/1701.01010
Autor:
Harremoës, Peter
The notion of Bregman divergence and sufficiency will be defined on general convex state spaces. It is demonstrated that only spectral sets can have a Bregman divergence that satisfies a sufficiency condition. Positive elements with trace 1 in a Jord
Externí odkaz:
http://arxiv.org/abs/1607.02259