English
Related papers

Related papers: Discretizing Distributions with Exact Moments: Err…

200 papers

We consider special upwinding Petrov-Galerkin discretizations for convection-diffusion problems. For the one dimensional case with a standard continuous linear element as the trial space and a special exponential bubble test space, we prove…

Numerical Analysis · Mathematics 2025-09-08 Constantin Bacuta

This is the second part of study on the optimal convergence rate of the explicit Euler discretization in time for the convection-diffusion equations [Appl. Math. Lett. \textbf{131} (2022) 108048] which focuses on high-dimensional…

Numerical Analysis · Mathematics 2022-05-13 Qifeng Zhang , Jiyuan Zhang , Zhi-zhong Sun

The Kullback-Leibler (KL) divergence is frequently used in data science. For discrete distributions on large state spaces, approximations of probability vectors may result in a few small negative entries, rendering the KL divergence…

Strong approximation errors of both finite element semi-discretization and spatio-temporal full discretization are analyzed for the stochastic Allen-Cahn equation driven by additive noise in space dimension $d \leq 3$. The full…

Numerical Analysis · Mathematics 2020-08-04 Ruisheng Qi , Xiaojie Wang

We consider the problem of estimating the population probability distribution given a finite set of multivariate samples, using the maximum entropy approach. In strict keeping with Jaynes' original definition, our precise formulation of the…

Data Analysis, Statistics and Probability · Physics 2007-07-13 Sabbir Rahman , Mahbub Majumdar

An elementary approach to characterizing the impact of noise scheduling and time discretization in generative diffusion models is developed. We first utilize the Cram\'er-Rao bound to identify the Gaussian setting as a fundamental…

Information Theory · Computer Science 2026-02-10 Qiang Sun , H. Vincent Poor , Wenyi Zhang

In Bayesian statistics probability distributions express beliefs. However, for many problems the beliefs cannot be computed analytically and approximations of beliefs are needed. We seek a loss function that quantifies how "embarrassing" it…

Statistics Theory · Mathematics 2017-08-07 Reimar H. Leike , Torsten A. Enßlin

We consider linear reaction-diffusion equations posed on unbounded domains, and discretized by adaptive Lagrange finite elements. To obtain finite-dimensional spaces, it is necessary to introduce a truncation boundary, whereby only a…

Numerical Analysis · Mathematics 2025-11-13 Théophile Chaumont-Frelet , Gregor Gantner

A broad set of sufficient conditions that guarantees the existence of the maximum entropy (maxent) distribution consistent with specified bounds on certain generalized moments is derived. Most results in the literature are either focused on…

Information Theory · Computer Science 2009-09-29 Prakash Ishwar , Pierre Moulin

The minimum rate needed to accurately approximate a product distribution based on an unnormalized informational divergence is shown to be a mutual information. This result subsumes results of Wyner on common information and Han-Verd\'{u} on…

Information Theory · Computer Science 2013-05-14 Jie Hou , Gerhard Kramer

The privacy loss distribution (PLD) provides a tight characterization of the privacy loss of a mechanism in the context of differential privacy (DP). Recent work has shown that PLD-based accounting allows for tighter $(\varepsilon,…

Data Structures and Algorithms · Computer Science 2022-07-12 Vadym Doroshenko , Badih Ghazi , Pritish Kamath , Ravi Kumar , Pasin Manurangsi

Density-based directed distances -- particularly known as divergences -- between probability distributions are widely used in statistics as well as in the adjacent research fields of information theory, artificial intelligence and machine…

Statistics Theory · Mathematics 2022-03-03 Michel Broniatowski , Wolfgang Stummer

A rich line of recent work has studied distributionally robust learning approaches that seek to learn a hypothesis that performs well, in the worst-case, on many different distributions over a population. We argue that although the most…

Machine Learning · Computer Science 2024-05-10 Jabari Hastings , Christopher Jung , Charlotte Peale , Vasilis Syrgkanis

We study Gaussian approximations to the distribution of a diffusion. The approximations are easy to compute: they are defined by two simple ordinary differential equations for the mean and the covariance. Time correlations can also be…

Probability · Mathematics 2016-05-20 Daniel Sanz-Alonso , Andrew M. Stuart

Recently, continual learning has received a lot of attention. One of the significant problems is the occurrence of \emph{concept drift}, which consists of changing probabilistic characteristics of the incoming data. In the case of the…

Machine Learning · Computer Science 2022-10-11 Sebastián Basterrech , Michal Woźniak

The state-of-the-art methods for estimating high-dimensional covariance matrices all shrink the eigenvalues of the sample covariance matrix towards a data-insensitive shrinkage target. The underlying shrinkage transformation is either…

Machine Learning · Statistics 2025-11-25 Man-Chung Yue , Yves Rychener , Daniel Kuhn , Viet Anh Nguyen

Entropy based ideas find wide-ranging applications in finance for calibrating models of portfolio risk as well as options pricing. The abstracted problem, extensively studied in the literature, corresponds to finding a probability measure…

Statistical Finance · Quantitative Finance 2014-11-04 Santanu Dey , Sandeep Juneja , Karthyek R. A. Murthy

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible while constrained to match empirically estimated feature expectations. However, in many real-world…

Machine Learning · Computer Science 2022-08-16 Kenneth Bogert , Yikang Gui , Prashant Doshi

We study the problem of discrete distribution estimation in KL divergence and provide concentration bounds for the Laplace estimator. We show that the deviation from mean scales as $\sqrt{k}/n$ when $n \ge k$, improving upon the best prior…

Machine Learning · Statistics 2023-06-14 Clément L. Canonne , Ziteng Sun , Ananda Theertha Suresh

We consider a linear ill-posed equation in the Hilbert space setting. Multiple independent unbiased measurements of the right hand side are available. A natural approach is to take the average of the measurements as an approximation of the…

Numerical Analysis · Mathematics 2021-09-01 Tim Jahn