paper-with-me

홈 › Papers

Collective Graphical Models

2011-12-01 · NeurIPS 2011 12 · Daniel R. Sheldon, Thomas G. Dietterich

There are many settings in which we wish to fit a model of the behavior of individuals but where our data consist only of aggregate information (counts or low-dimensional contingency tables). This paper introduces Collective Graphical Models---a framework for modeling and probabilistic inference that operates directly on the sufficient statistics of the individual model. We derive a highly-efficient Gibbs sampling algorithm for sampling from the posterior distribution of the sufficient statistics conditioned on noisy aggregate observations, prove its correctness, and demonstrate its effectiveness experimentally.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Differentially Private Learning of Undirected Graphical Models using Collective Graphical Models

2017-06-14 · Garrett Bernstein, Ryan McKenna, Tao Sun, Daniel Sheldon 외

We investigate the problem of learning discrete, undirected graphical models in a differentially private way. We show that the approach of releasing noisy sufficient statistics using the Laplace mechanism achieves a good…

Gaussian Approximation of Collective Graphical Models

2014-05-20 · Li-Ping Liu, Daniel Sheldon, Thomas G. Dietterich

The Collective Graphical Model (CGM) models a population of independent and identically distributed individuals when only collective statistics (i.e., counts of individuals) are observed. Exact inference in CGMs is intra…

Probabilistic Optimal Transport based on Collective Graphical Models

2020-06-16 · Yasunori Akagi, Yusuke Tanaka, Tomoharu Iwata, Takeshi Kurashima 외

Optimal Transport (OT) is being widely used in various fields such as machine learning and computer vision, as it is a powerful tool for measuring the similarity between probability distributions and histograms. In previ…

Robust Collective Classification against Structural Attacks

2020-07-26 · Kai Zhou, Yevgeniy Vorobeychik

Collective learning methods exploit relations among data points to enhance classification performance. However, such relations, represented as edges in the underlying graphical model, expose an extra attack surface to th…

Adversarial RobustnessClassificationGeneral ClassificationTransductive Learning

Bethe Projections for Non-Local Inference

2015-03-04 · Luke Vilnis, David Belanger, Daniel Sheldon, Andrew McCallum

Many inference problems in structured prediction are naturally solved by augmenting a tractable dependency structure with complex, non-local auxiliary objectives. This includes the mean field family of variational infere…

Handwriting RecognitionStructured PredictionVariational Inference