UAI 2014 Inference Competition

Introduction

We are pleased to announce an upcoming evaluation of probabilistic approximate inference algorithms, as part of the UAI 2014 conference. All researchers working on inference in graphical models and statistical relational models are encouraged to participate.

The evaluation will focus on the following computational tasks:

• Computing the partition function and probability of evidence (PR inference)

• Computing the marginal probability distribution over a variable given evidence (MAR inference)

• Computing the most likely assignment to all variables given evidence (MAP Inference)

New this year

The following two evaluations/competitions will be run on experimental basis:

• Computing the most likely assignment to a subset of variables given evidence (Marginal MAP inference)

• Weight (or Parameter) Learning (we will use solvers that compute marginal probabilities to do this). Therefore, if you participate in the MAR inference task, you will be automatically entered in this task.

Submitted algorithms can compete in some or all of these tasks.

Sample Problems

• 1.uai 1.uai.evid

• 2.uai 2.uai.evid

• 3.uai 3.uai.evid

• 4.uai 4.uai.evid

UAI File Format Descriptions

• Model Format

• Evidence Format

• Query variables, only applies to the marginal MAP task

• Result/Output format

Prizes

• To be announced later. However, you will get bragging rights if you win and we won't reveal your names if you lose. Therefore, please compete!