English
Related papers

Related papers: Exponential families from a single KL identity

200 papers

Probabilistic Latent Tensor Factorization (PLTF) is a recently proposed probabilistic framework for modelling multi-way data. Not only the common tensor factorization models but also any arbitrary tensor factorization structure can be…

Computation · Statistics 2014-09-30 Beyza Ermis , Y. Kenan Yılmaz , A. Taylan Cemgil , Evrim Acar

Coupling arguments are a central tool for bounding the deviation between two stochastic processes, but traditionally have been limited to Wasserstein metrics. In this paper, we apply the shifted composition rule--an information-theoretic…

Statistics Theory · Mathematics 2024-12-25 Jason M. Altschuler , Sinho Chewi

While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. The theoretical work…

Machine Learning · Computer Science 2019-07-02 Yu Bai , Tengyu Ma , Andrej Risteski

The Kullback-Leibler (KL) divergence is a fundamental equation of information theory that quantifies the proximity of two probability distributions. Although difficult to understand by examining the equation, an intuition and understanding…

Information Theory · Computer Science 2014-04-09 Jonathon Shlens

This work presents an upper-bound to value that the Kullback-Leibler (KL) divergence can reach for a class of probability distributions called quantum distributions (QD). The aim is to find a distribution $U$ which maximizes the KL…

Machine Learning · Computer Science 2020-12-11 Vincenzo Bonnici

The estimation of categorical distributions under marginal constraints summarizing some sample from a population in the most-generalizable way is key for many machine-learning and data-driven approaches. We provide a parameter-agnostic…

High Energy Physics - Theory · Physics 2023-11-17 Orestis Loukas , Ho Ryun Chung

In this paper, we introduce differential exponential maps in Cartesian differential categories, which generalizes the exponential function $e^x$ from classical differential calculus. A differential exponential map is an endomorphism which…

Category Theory · Mathematics 2020-07-20 Jean-Simon Pacaud Lemay

We provide a classification of graphical models according to their representation as subfamilies of exponential families. Undirected graphical models with no hidden variables are linear exponential families (LEFs), directed acyclic…

Machine Learning · Computer Science 2013-02-01 Dan Geiger , Christopher Meek

Identifying the algebra of exponential generating series with the shuffle algebra of formal power series, one can define an exponential map ${\mathop{exp}}_!:X\mathbb K[[X]]\longrightarrow 1+X\mathbb K[[X]]$ for the associated Lie group…

Number Theory · Mathematics 2019-04-22 Roland Bacher

In their fundamental paper on cubic variance functions, Letac and Mora (The Annals of Statistics,1990) presented a systematic, rigorous and comprehensive study of natural exponential families on the real line, their characterization through…

Statistics Theory · Mathematics 2021-02-05 Shaul K. Bar-Lev , Ad Ridder

We study a general factor analysis framework where the $n$-by-$p$ data matrix is assumed to follow a general exponential family distribution entry-wise. While this model framework has been proposed before, we here further relax its…

Methodology · Statistics 2025-12-02 Liang Wang , Luis Carvalho

We describe convolutional deep exponential families (CDEFs) in this paper. CDEFs are built based on deep exponential families, deep probabilistic models that capture the hierarchical dependence between latent variables. CDEFs greatly reduce…

Machine Learning · Statistics 2021-10-29 Chengkuan Hong , Christian R. Shelton

A $k$-modal probability distribution over the discrete domain $\{1,...,n\}$ is one whose histogram has at most $k$ "peaks" and "valleys." Such distributions are natural generalizations of monotone ($k=0$) and unimodal ($k=1$) probability…

Data Structures and Algorithms · Computer Science 2014-09-16 Constantinos Daskalakis , Ilias Diakonikolas , Rocco A. Servedio

In the probability theory \emph{selfdecomposable, or class $L_0$ distributions} play an important role as they are limiting distributions of normalized partial sums of sequences of independent, not necessarily identically distributed,…

Probability · Mathematics 2023-01-30 Zbigniew J. Jurek

The remarkable empirical performance of distributional reinforcement learning (RL) has garnered increasing attention to understanding its theoretical advantages over classical RL. By decomposing the categorical distributional loss commonly…

Machine Learning · Computer Science 2025-12-25 Ke Sun , Yingnan Zhao , Enze Shi , Yafei Wang , Xiaodong Yan , Bei Jiang , Linglong Kong

We introduce a new approach to learning in hierarchical latent-variable generative models called the "distributed distributional code Helmholtz machine", which emphasises flexibility and accuracy in the inferential process. In common with…

Machine Learning · Statistics 2018-05-29 Eszter Vertes , Maneesh Sahani

Recent Reinforcement Learning (RL) algorithms making use of Kullback-Leibler (KL) regularization as a core component have shown outstanding performance. Yet, only little is understood theoretically about why KL regularization helps, so far.…

Machine Learning · Computer Science 2021-01-07 Nino Vieillard , Tadashi Kozuno , Bruno Scherrer , Olivier Pietquin , Rémi Munos , Matthieu Geist

Recent years have seen advances in generalization bounds for noisy stochastic algorithms, especially stochastic gradient Langevin dynamics (SGLD) based on stability (Mou et al., 2018; Li et al., 2020) and information theoretic approaches…

Machine Learning · Computer Science 2022-11-02 Arindam Banerjee , Tiancong Chen , Xinyan Li , Yingxue Zhou

We revisit the method of mixture technique, also known as the Laplace method, to study the concentration phenomenon in generic exponential families. Combining the properties of Bregman divergence associated with log-partition function of…

Machine Learning · Computer Science 2023-07-14 Sayak Ray Chowdhury , Patrick Saux , Odalric-Ambrym Maillard , Aditya Gopalan

Recently we introduced a family of $U(N)$ invariant Random Matrix Ensembles which is characterized by a parameter $\lambda$ describing logarithmic soft-confinement potentials $V(H) \sim [\ln H]^{(1+\lambda)} \:(\lambda>0$). We showed that…

Disordered Systems and Neural Networks · Physics 2013-05-29 Jinmyung Choi , K. A. Muttalib