English
Related papers

Related papers: R\'enyi Divergence in General Hidden Markov Models

200 papers

Two R\'{e}nyi-type generalizations of the Shannon cross-entropy, the R\'{e}nyi cross-entropy and the Natural R\'{e}nyi cross-entropy, were recently used as loss functions for the improved design of deep learning generative adversarial…

Information Theory · Computer Science 2022-10-06 Ferenc Cole Thierrin , Fady Alajaji , Tamás Linder

We propose a new family of regularized R\'enyi divergences parametrized not only by the order $\alpha$ but also by a variational function space. These new objects are defined by taking the infimal convolution of the standard R\'enyi…

Machine Learning · Statistics 2023-02-16 Jeremiah Birrell , Yannis Pantazis , Paul Dupuis , Markos A. Katsoulakis , Luc Rey-Bellet

There are many applications that benefit from computing the exact divergence between 2 discrete probability measures, including machine learning. Unfortunately, in the absence of any assumptions on the structure or independencies within…

Machine Learning · Computer Science 2023-10-16 Loong Kuan Lee , Nico Piatkowski , François Petitjean , Geoffrey I. Webb

The sandwiched R\'enyi divergences of two finite-dimensional density operators quantify their asymptotic distinguishability in the strong converse domain. This establishes the sandwiched R\'enyi divergences as the operationally relevant…

Quantum Physics · Physics 2025-08-12 Milán Mosonyi

This paper gives a method for computing distributions associated with patterns in the state sequence of a hidden Markov model, conditional on observing all or part of the observation sequence. Probabilities are computed for very general…

Methodology · Statistics 2007-12-18 John A. D. Aston , Donald E. K. Martin

Discrete normal distributions are defined as the distributions with prescribed means and covariance matrices which maximize entropy on the integer lattice support. The set of discrete normal distributions form an exponential family with…

Information Theory · Computer Science 2022-01-25 Frank Nielsen

In this work we introduce a family of transformations, named \textit{divergence transformations}, interpolating between any pair of probability density functions sharing the same support. We prove the remarkable property that the whole…

Mathematical Physics · Physics 2025-12-15 Razvan Gabriel Iagar , David Puertas-Centeno , Elio V. Toranzo

We present new methods for assessing the privacy guarantees of an algorithm with regard to R\'enyi Differential Privacy. To the best of our knowledge, this work is the first to address this problem in a black-box scenario, where only…

Cryptography and Security · Computer Science 2022-12-12 Tim Kutta , Önder Askin , Martin Dunsche

The Kullback-Leibler divergence or relative entropy is an information-theoretic measure between statistical models that play an important role in measuring a distance between random variables. In the study of complex systems, random fields…

Information Theory · Computer Science 2022-03-25 Alexandre L. M. Levada

Discovering and classifying non-trivial mixed states and mixed state phase transitions are some of the most important current issues in condensed matter and quantum information. In this study, we investigate some non-trivial mixed states…

Quantum Physics · Physics 2025-05-06 Yoshihito Kuno , Takahiro Orito , Ikuo Ichinose

We give an overview of various results and methods related to information-theoretic distances of R\'enyi type in the light of their applications to the central limit theorem (CLT). The first part (Sections 1-9) is devoted to the total…

Information Theory · Computer Science 2025-03-07 S. G. Bobkov , G. P. Chistyakov , F. Götze

We introduce a multivariate hidden Markov model to jointly cluster time-series observations with different support, i.e. circular and linear. Relying on the general projected normal distribution, our approach allows for bimodal and/or…

Applications · Statistics 2015-01-27 Gianluca Mastrantonio , Antonello Maruotti , Giovanna Jona Lasinio

We consider a bivariate Markov chain $Z=\{Z_k\}_{k \geq 1}=\{(X_k,Y_k)\}_{k \geq 1}$ taking values on product space ${\cal Z}={\cal X} \times{ \cal Y}$, where ${\cal X}$ is possibly uncountable space and ${\cal Y}=\{1,\ldots, |{\cal Y}|\}$…

Probability · Mathematics 2021-03-10 Jüri Lember , Joonas Sova

We present and analyse three online algorithms for learning in discrete Hidden Markov Models (HMMs) and compare them with the Baldi-Chauvin Algorithm. Using the Kullback-Leibler divergence as a measure of generalisation error we draw…

Machine Learning · Statistics 2007-08-20 Roberto C. Alamino , Nestor Caticha

We introduce an extension of finite mixture models by incorporating skew-normal distributions within a Hidden Markov Model framework. By assuming a constant transition probability matrix and allowing emission distributions to vary according…

Methodology · Statistics 2025-09-25 Andrea Nigri , Marco Forti , Han Lin Shang

We consider Hidden Markov Models that emit sequences of observations that are drawn from continuous distributions. For example, such a model may emit a sequence of numbers, each of which is drawn from a uniform distribution, but the support…

Logic in Computer Science · Computer Science 2020-09-29 Oscar Darwin , Stefan Kiefer

We express the joint R\'enyi entropy of progressively censored order statistics in terms of an incomplete integral of the hazard function, and provide a simple estimate of the joint R\'enyi entropy of progressively Type-II censored data.…

Methodology · Statistics 2013-03-25 Akram Kohansal , Saeid Rezakhah

MCMC methods (Monte Carlo Markov Chain) are a class of methods used to perform simulations per a probability distribution $P$. These methods are often used when we have difficulties to directly sample per a given probability distribution…

Methodology · Statistics 2014-01-21 Papa Ngom , Badiassiatta Don Bosco Diatta

We propose R\'enyi information generating function and discuss its properties. A connection between the R\'enyi information generating function and the diversity index is proposed for discrete type random variables. The relation between the…

Statistics Theory · Mathematics 2025-02-25 Shital Saha , Suchandan Kayal , N. Balakrishnan

For nonlinear supervised learning models, assessing the importance of predictor variables or their interactions is not straightforward because it can vary in the domain of the variables. Importance can be assessed locally with sensitivity…

Methodology · Statistics 2021-12-14 Topi Paananen , Michael Riis Andersen , Aki Vehtari