Probably almost discriminative learning

Probably Approximately Correct Learning

This paper surveys some recent theoretical results on the efficiency of machine learning algorithms. The main tool described is the notion of Probably Approximately Correct (PAC) 1 earning, introduced by Valiant. We define this learning model and then look at sorne of the results obtained in it. We then consider some criticisms of the PAC model and the extensions proposed to address these criti...

Probably Approximately Correct Learning

Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm. of empirical and explanation-based learning algo

Probably Approximately Metric-Fair Learning

We study fairness in machine learning. A learning algorithm, given a training set drawn from an underlying population, learns a classifier that will be used to make decisions about individuals. The concern is that this classifier’s decisions might be discriminatory, favoring certain subpopulations over others. The seminal work of Dwork et al. [ITCS 2012] introduced fairness through awareness, p...

Refutably Probably Approximately Correct Learning

Discriminative vs Informative Learning

The goal of pattern classification can be approached from two points of view: informative where the classifier learns the class densities, or discriminative where the focus is on learning the class boundaries without regard to the underlying class densities. We review and synthesize the tradeoffs between these two approaches for simple classifiers, and extend the results to modern techniques su...