Machine Learning Markets

TL;DR

This paper introduces machine learning markets as a flexible, utility-based framework for model combination and inference in probabilistic systems, enabling parallelized learning and inference methods.

Contribution

It defines multivariate machine learning markets with a utility-based analysis, connecting market mechanisms to model combination and inference techniques.

Findings

Markets can implement product and mixture of expert models.

Markets facilitate flexible model combinations with diverse utility functions.

Market mechanisms enable parallelized probabilistic inference.

Abstract

Prediction markets show considerable promise for developing flexible mechanisms for machine learning. Here, machine learning markets for multivariate systems are defined, and a utility-based framework is established for their analysis. This differs from the usual approach of defining static betting functions. It is shown that such markets can implement model combination methods used in machine learning, such as product of expert and mixture of expert approaches as equilibrium pricing models, by varying agent utility functions. They can also implement models composed of local potentials, and message passing methods. Prediction markets also allow for more flexible combinations, by combining multiple different utility functions. Conversely, the market mechanisms implement inference in the relevant probabilistic models. This means that market mechanism can be utilized for implementing parallelized model building and inference for probabilistic modelling.