English
Related papers

Related papers: Learning probabilities from random observables in …

200 papers

In Bayesian inference, we seek to compute information about random variables such as moments or quantiles on the basis of {available data} and prior information. When the distribution of random variables is {intractable}, Monte Carlo (MC)…

Statistics Theory · Mathematics 2021-04-06 Alec Koppel , Amrit Singh Bedi , Brian M. Sadler , Victor Elvira

Vanilla variational inference finds an optimal approximation to the Bayesian posterior distribution, but even the exact Bayesian posterior is often not meaningful under model misspecification. We propose predictive variational inference…

Machine Learning · Statistics 2026-03-31 Jinlin Lai , Antonio Linero , Yuling Yao

A common approach to statistical learning with big-data is to randomly split it among $m$ machines and learn the parameter of interest by averaging the $m$ individual estimates. In this paper, focusing on empirical risk minimization, or…

Machine Learning · Statistics 2016-06-14 Jonathan Rosenblatt , Boaz Nadler

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

We study density estimation for classes of shift-invariant distributions over $\mathbb{R}^d$. A multidimensional distribution is "shift-invariant" if, roughly speaking, it is close in total variation distance to a small shift of it in any…

Machine Learning · Computer Science 2018-11-12 Anindya De , Philip M. Long , Rocco A. Servedio

We study the problem of learning from unlabeled samples very general statistical mixture models on large finite sets. Specifically, the model to be learned, $\vartheta$, is a probability distribution over probability distributions $p$,…

Machine Learning · Computer Science 2015-04-13 Jian Li , Yuval Rabani , Leonard J. Schulman , Chaitanya Swamy

This paper considers the problem of estimating a power-law degree distribution of an undirected network using sampled data. Although power-law degree distributions are ubiquitous in nature, the widely used parametric methods for estimating…

Social and Information Networks · Computer Science 2021-03-09 Buddhika Nettasinghe , Vikram Krishnamurthy

We present an algorithmic approach to estimate the value distributions of random variables of probabilistic loops whose statistical moments are (partially) known. Based on these moments, we apply two statistical methods, Maximum Entropy and…

Simple Monte Carlo is a versatile computational method with a convergence rate of $O(n^{-1/2})$. It can be used to estimate the means of random variables whose distributions are unknown. Bernoulli random variables, $Y$, are widely used to…

Numerical Analysis · Mathematics 2014-11-06 Lan Jiang , Fred J. Hickernell

Importance sampling of target probability distributions belonging to a given convex class is considered. Motivated by previous results, the cost of importance sampling is quantified using the relative entropy of the target with respect to…

Numerical Analysis · Mathematics 2022-12-09 Frédéric Cérou , Patrick Héas , Mathias Rousset

This paper investigates a novel offline change-point detection problem from an information-theoretic perspective. In contrast to most related works, we assume that the knowledge of the underlying pre- and post-change distributions are not…

Information Theory · Computer Science 2021-10-05 Haiyun He , Qiaosheng Zhang , Vincent Y. F. Tan

Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks,…

Machine Learning · Statistics 2024-12-17 Mingtian Zhang , Thomas Bird , Raza Habib , Tianlin Xu , David Barber

Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only learn some aspects (e.g., cluster or…

Machine Learning · Computer Science 2019-05-16 Charlotte Bunne , David Alvarez-Melis , Andreas Krause , Stefanie Jegelka

Calibration methods have been widely studied in survey sampling over the last decades. Viewing calibration as an inverse problem, we extend the calibration technique by using a maximum entropy method. Finding the optimal weights is achieved…

Methodology · Statistics 2009-09-23 Fabrice Gamboa , Jean-Michel Loubes , Paul Rochet

While efficient distribution learning is no doubt behind the groundbreaking success of diffusion modeling, its theoretical guarantees are quite limited. In this paper, we provide the first rigorous analysis on approximation and…

Machine Learning · Statistics 2023-03-06 Kazusato Oko , Shunta Akiyama , Taiji Suzuki

We consider the problem of estimating how well a model class is capable of fitting a distribution of labeled data. We show that it is often possible to accurately estimate this "learnability" even when given an amount of data that is too…

Machine Learning · Computer Science 2019-03-26 Weihao Kong , Gregory Valiant

We describe and analyze a broad class of mixture models for real-valued multivariate data in which the probability density of observations within each component of the model is represented as an arbitrary combination of basis functions.…

Methodology · Statistics 2025-02-28 M. E. J. Newman

Probability density function estimation with weighted samples is the main foundation of all adaptive importance sampling algorithms. Classically, a target distribution is approximated either by a non-parametric model or within a parametric…

Machine Learning · Computer Science 2023-10-16 Julien Demange-Chryst , François Bachoc , Jérôme Morio , Timothé Krauth

Maximum entropy method is a constructive criterion for setting up a probability distribution maximally non-committal to missing information on the basis of partial knowledge, usually stated as constrains on expectation values of some…

Statistical Mechanics · Physics 2015-07-20 Jorge Fernandez-de-Cossio , Jorge Fernandez-de-Cossio Diaz

A pedagogical account of some aspects of Extreme Value Statistics (EVS) is presented from the somewhat non-standard viewpoint of Large Deviation Theory. We address the following problem: given a set of $N$ i.i.d. random variables…

Statistical Mechanics · Physics 2015-09-02 Pierpaolo Vivo