English
Related papers

Related papers: New Understanding of the Bethe Approximation and t…

200 papers

Graphical models for finite-dimensional spin glasses and real-world combinatorial optimization and satisfaction problems usually have an abundant number of short loops. The cluster variation method and its extension, the region graph…

Disordered Systems and Neural Networks · Physics 2013-07-29 Haijun Zhou , Chuang Wang

In statistical physics and information theory, although the exponent of the partition function is often of our primary interest, there are cases where one needs more detailed information. In this paper, we present a general framework to…

Information Theory · Computer Science 2012-02-06 Ryuhei Mori , Toshiyuki Tanaka

Can a deep neural network be approximated by a small decision tree based on simple features? This question and its variants are behind the growing demand for machine learning models that are *interpretable* by humans. In this work we study…

Machine Learning · Computer Science 2024-06-18 Marco Bressan , Nicolò Cesa-Bianchi , Emmanuel Esposito , Yishay Mansour , Shay Moran , Maximilian Thiessen

Bayesian inference allows us to define a posterior distribution over the weights of a generic neural network (NN). Exact posteriors are usually intractable, in which case approximations can be employed. One such approximation - variational…

Machine Learning · Computer Science 2026-01-30 Andrew Millard , Joshua Murphy , Peter Green , Simon Maskell

Belief Propagation (BP) is a powerful algorithm for distributed inference in probabilistic graphical models, however it quickly becomes infeasible for practical compute and memory budgets. Many efficient, non-parametric forms of BP have…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-30 Tom Yates , Yuzhou Cheng , Ignacio Alzugaray , Danyal Akarca , Pedro A. M. Mediano , Andrew J. Davison

Tensor network contraction on arbitrary graphs is a fundamental computational challenge with applications ranging from quantum simulation to error correction. While belief propagation (BP) provides a powerful approximation algorithm for…

Quantum Physics · Physics 2025-10-28 Siddhant Midha , Yifan F. Zhang

Diffusion models, which convert noise into new data instances by learning to reverse a diffusion process, have become a cornerstone in contemporary generative modeling. In this work, we develop non-asymptotic convergence theory for a…

Machine Learning · Computer Science 2024-08-06 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

The asymptotic equipartition property (AEP) states that in the limit of a large number of independent and identically distributed (i.i.d.) random experiments, the output sequence is virtually certain to come from the typical set, each…

Quantum Physics · Physics 2025-06-04 Kun Fang , Hamza Fawzi , Omar Fawzi

We consider a model of random tree growth, where at each time unit a new vertex is added and attached to an already existing vertex chosen at random. The probability with which a vertex with degree $k$ is chosen is proportional to $w(k)$,…

Probability · Mathematics 2007-05-23 Anna Rudas , Balint Toth , Benedek Valko

We present a combinatorial characterization of the Bethe entropy function of a factor graph, such a characterization being in contrast to the original, analytical, definition of this function. We achieve this combinatorial characterization…

Information Theory · Computer Science 2013-11-05 Pascal O. Vontobel

Cloning, or approximate cloning, is one of basic operations in quantum information processing. In this paper, we deal with cloning of classical states, or probability distribution in asymptotic setting. We study the quality of the…

Quantum Physics · Physics 2011-11-22 Keiji Matsumoto

We provide a general framework for proving asymptotic equidistribution, convexity, and log concavity of coefficients of generating functions on arithmetic progressions. Our central tool is a variant of Wright's Circle Method proved by two…

Number Theory · Mathematics 2021-12-08 Giulia Cesana , William Craig , Joshua Males

Models often need to be constrained to a certain size for them to be considered interpretable. For example, a decision tree of depth 5 is much easier to understand than one of depth 50. Limiting model size, however, often reduces accuracy.…

Machine Learning · Computer Science 2020-07-02 Abhishek Ghose , Balaraman Ravindran

Bayesian inference provides a framework to combine various model components with shared parameters, allowing joint uncertainty estimation and the use of all available data sources. Unfortunately, misspecification of any part of the model…

Methodology · Statistics 2026-03-13 Emilia Pompe , Mikołaj J. Kasprzak , Pierre E. Jacob

We provide a general theorem on the asymptotic behavior of stochastic processes that conform to a relaxed supermartingale condition. The distinguishing feature of our result is that it provides quantitative convergence guarantees at a much…

Optimization and Control · Mathematics 2026-05-11 Morenikeji Neri , Nicholas Pischke , Thomas Powell

The beta process has recently been widely used as a nonparametric prior for different models in machine learning, including latent feature models. In this paper, we prove the asymptotic consistency of the finite dimensional approximation of…

Statistics Theory · Mathematics 2014-11-14 Luai Al Labadi , Mahmoud Zarepour

Laplace's method, a family of asymptotic methods used to approximate integrals, is presented as a potential candidate for the tool box of techniques used for knowledge acquisition and probabilistic inference in belief networks with…

Artificial Intelligence · Computer Science 2013-02-28 Adriano Azevedo-Filho , Ross D. Shachter

We analyze a reweighted version of the Kikuchi approximation for estimating the log partition function of a product distribution defined over a region graph. We establish sufficient conditions for the concavity of our reweighted objective…

Machine Learning · Statistics 2014-10-28 Po-Ling Loh , Andre Wibisono

Although Bayesian methods are robust and principled, their application in practice could be limited since they typically rely on computationally intensive Markov Chain Monte Carlo algorithms for their implementation. One possible solution…

Computation · Statistics 2015-10-06 Tian Chen , Jeffrey Streets , Babak Shahbaba

We research relations between optimal transport theory (OTT) and approximate Bayesian computation (ABC) possibly connected to relevant metrics defined on probability measures. Those of ABC are computational methods based on Bayesian…

Statistics Theory · Mathematics 2021-05-06 Marco Tarsia , Antonietta Mira , Daniele Cassani
‹ Prev 1 4 5 6 7 8 10 Next ›