paper-with-me

홈 › Papers

Estimating Functions of Probability Distributions from a Finite Set of Samples, Part 1: Bayes Estimators and the Shannon Entropy

1994-03-08 · David H. Wolpert, David R. Wolf

We present estimators for entropy and other functions of a discrete probability distribution when the data is a finite sample drawn from that probability distribution. In particular, for the case when the probability distribution is a joint distribution, we present finite sample estimators for the mutual information, covariance, and chi-squared functions of that probability distribution.

📄 PDF Abstract BibTeX arXiv:comp-gas/9403001

Code (1)

aryamanarora/entropy-estimation

Similar Papers 제목 키워드 기반

Data-Driven Reachability analysis and Support set Estimation with Christoffel Functions

2021-12-18 · Alex Devonport, Forest Yang, Laurent El Ghaoui, Murat Arcak

We present algorithms for estimating the forward reachable set of a dynamical system using only a finite collection of independent and identically distributed samples. The produced estimate is the sublevel set of a funct…

Sublinear Algorithms for Wasserstein and Total Variation Distances: Applications to Fairness and Privacy Auditing

2025-03-10 · Debabrota Basu, Debarshi Chanda

Resource-efficiently computing representations of probability distributions and the distances between them while only having access to the samples is a fundamental and useful problem across mathematical sciences. In this…

FairnessFederated Learning

Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits

2015-07-16 · Alexandra Carpentier, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos 외

In this paper, we study the problem of estimating uniformly well the mean values of several distributions given a finite budget of samples. If the variance of the distributions were known, one could design an optimal sam…

Active LearningMulti-Armed Bandits

Neural Monge Map estimation and its applications

2021-06-07 · Jiaojiao Fan, Shu Liu, Shaojun Ma, Haomin Zhou 외

Monge map refers to the optimal transport map between two probability distributions and provides a principled approach to transform one distribution to another. Neural network based optimal transport map solver has gaine…

Image GenerationImage InpaintingText to Image GenerationText-to-Image Generation

On the Estimation of Information Measures of Continuous Distributions

2020-02-07 · Georg Pichler, Pablo Piantanida, Günther Koliander

The estimation of information measures of continuous distributions based on samples is a fundamental problem in statistics and machine learning. In this paper, we analyze estimates of differential entropy in $K$-dimensio…