English
Related papers

Related papers: Variational Bounds for the Generalized Random Ener…

200 papers

The presence of unobserved node specific heterogeneity in Exponential Random Graph Models (ERGM) is a general concern, both with respect to model validity as well as estimation instability. We therefore extend the ERGM by including node…

Computation · Statistics 2021-12-24 Sevag Kevork , Göran Kauermann

The alternative replica technique which involve summation over all integer momenta of the partition function and which does not require analytic continuation to non-integer values of the replica parameter $n$ is discussed. In terms of this…

Disordered Systems and Neural Networks · Physics 2015-05-27 Victor Dotsenko

We study the spin glass system consisting of a Random Energy Model coupled with a random magnetic field. This system was investigated by de Oliveira Filho, da Costa and Yokoi (Phys. Rev. E 74 [2006]) who computed the free energy. In this…

Probability · Mathematics 2015-06-18 Louis-Pierre Arguin , Nicola Kistler

Using a capacity approach, and the theory of measure's perturbation of Dirichlet forms, we give the probabilistic representation of the General Robin boundary value problems on an arbitrary domain $\Omega$, involving smooth measures, which…

Probability · Mathematics 2013-03-26 Khalid Akhlil

We address regularised versions of the Expectation-Maximisation (EM) algorithm for Generalised Linear Mixed Models (GLMM) in the context of panel data (measured on several individuals at different time points). A random response y is…

Methodology · Statistics 2019-08-21 Jocelyn Chauvet , Catherine Trottier , Xavier Bry

Important problems in causal inference, economics, and, more generally, robust machine learning can be expressed as conditional moment restrictions, but estimation becomes challenging as it requires solving a continuum of unconditional…

Machine Learning · Computer Science 2024-02-19 Heiner Kremer , Jia-Jie Zhu , Krikamol Muandet , Bernhard Schölkopf

We consider the free energy of a mean-field quantum spin glass described by a $ p $-spin interaction and a transversal magnetic field. Recent rigorous results for the case $ p= \infty $, i.e. the quantum random energy model (QREM), are…

Mathematical Physics · Physics 2021-09-13 Chokri Manai , Simone Warzel

In this paper we provide explicit upper bounds on some distances between the (law of the) output of a random Gaussian NN and (the law of) a random Gaussian vector. Our results concern both shallow random Gaussian neural networks with…

The average gamma-ray spectrum $^{114}$Cd after thermal neutron capture in $^{113}$Cd was evaluated in units of mb/MeV. Two approaches are considered for estimation of the average gamma-ray spectrum with normalization of the experimental…

Nuclear Experiment · Physics 2022-03-01 V. A. Plujko , O. M. Gorbachenko , K. M. Solodovnyk , V. M. Petrenko

As a classical generative modeling approach, energy-based models have the natural advantage of flexibility in the form of the energy function. Recently, energy-based models have achieved great success in modeling high-dimensional data in…

Machine Learning · Computer Science 2024-01-19 Taoli Cheng , Aaron Courville

By the use of the variational method with exponential trial functions the upper and lower bounds of energy are calculated for a number of non-relativistic three-body Coulomb and nuclear systems. The formulas for calculation of upper and…

Atomic Physics · Physics 2007-05-23 A. G. Donchev , N. N. Kolesnikov , V. I. Tarasov

The empirical risk minimization (ERM) problem with relative entropy regularization (ERM-RER) is investigated under the assumption that the reference measure is a $\sigma$-finite measure, and not necessarily a probability measure. Under this…

Statistics Theory · Mathematics 2024-04-09 Samir M. Perlaza , Gaetan Bisson , Iñaki Esnaola , Alain Jean-Marie , Stefano Rini

Practitioners in diverse fields such as healthcare, economics and education are eager to apply machine learning to improve decision making. The cost and impracticality of performing experiments and a recent monumental increase in electronic…

Machine Learning · Computer Science 2023-08-01 Fredrik D. Johansson , Uri Shalit , Nathan Kallus , David Sontag

A general random effects model is proposed that allows for continuous as well as discrete distributions of the responses. Responses can be unrestricted continuous, bounded continuous, binary, ordered categorical or given in the form of…

Methodology · Statistics 2024-04-30 Gerhard Tutz

Bounds on the log partition function are important in a variety of contexts, including approximate inference, model fitting, decision theory, and large deviations analysis. We introduce a new class of upper bounds on the log partition…

Machine Learning · Computer Science 2013-01-07 Martin Wainwright , Tommi S. Jaakkola , Alan Willsky

We develop approximate estimation methods for exponential random graph models (ERGMs), whose likelihood is proportional to an intractable normalizing constant. The usual approach approximates this constant with Monte Carlo simulations,…

Methodology · Statistics 2023-01-11 Angelo Mele , Lingjiong Zhu

An information-theoretic upper bound on the generalization error of supervised learning algorithms is derived. The bound is constructed in terms of the mutual information between each individual training sample and the output of the…

Machine Learning · Computer Science 2020-08-06 Yuheng Bu , Shaofeng Zou , Venugopal V. Veeravalli

While deep learning-based classification is generally tackled using standardized approaches, a wide variety of techniques are employed for regression. In computer vision, one particularly popular such technique is that of confidence-based…

Machine Learning · Computer Science 2020-07-21 Fredrik K. Gustafsson , Martin Danelljan , Goutam Bhat , Thomas B. Schön

The construction of models from data is a significant contributor to the energetic costs of computation. Because of this, understanding how foundational thermodynamic bounds apply to modeling algorithms will be increasingly important. Here,…

Statistical Mechanics · Physics 2026-05-20 Samuel H. D'Ambrosia , Sultan M. Daniels , Michael R. DeWeese , Anant Sahai

We consider a generalization of the variance-gamma (generalized asymmetric Laplace) distribution, defined as a normal mean - variance mixture with a gamma mixing distribution. While this model is typically studied in the univariate setting,…

Methodology · Statistics 2026-05-04 Tomasz J. Kozubowski , Andrey Sarantsev , James A. Spiker