No free theory choice from machine learning

UNDERSTANDING MACHINE LEARNING From Theory to Algorithms

8803 Machine Learning Theory

We consider a learning problem specified as follows. We are given access to labeled examples (x, l) drawn from some distribution P over X × {−1, 1}, where X is an abstract instance space. The objective of a learning algorithm is to produce a classification function g : X → {−1, 1} whose error rate Pr(x,l)∼P [g(x) ̸= l] is low. We will consider learning algorithms that only access the points x th...

Designing social choice mechanisms using machine learning

Social choice studies ordinal preference and information aggregation with applications in high-stakes political elections as well as low-stakes movie rating websites. Recently, computational aspects of classical social choice mechanisms have been extensively investigated, yet not much has been done in designing new mechanisms with the help of computational techniques. In this paper, we outline ...

Conventional Machine Learning for Social Choice

Deciding the outcome of an election when voters have provided only partial orderings over their preferences requires voting rules that accommodate missing data. While existing techniques, including considerable recent work, address missingness through circumvention, we propose the novel application of conventional machine learning techniques to predict the missing components of ballots via late...

Rational Choice Theory: An Overview

It seems easy to accept that rationality involves many features that cannot be summarized in terms of some straightforward formula, such as binary consistency.  However, this recognition does not immediately lead to alternative characterizations that might be regarded as satisfactory, even though the inadequacies of the traditional assumptions of rational behavior standard used in economic theo...