Much of everyday human thinking and learning can be understood in terms of program induction: constructing a procedure that maps inputs to desired outputs, based on observing example input-output pairs.

In doing so, we define the agent's policy using the intensity and

Crucially, the neural model uses miniKanren's

In the current work we aim to close this gap.

In this paper, we consider online F-measure optimization (OFO). Unlike traditional performance metrics (e.g., classification error rate), F-measure is non-decomposable over training examples and is a non-convex function of model parameters, making it much more difficult to be optimized in an online fashion. Most existing results of OFO usually suffer from high memory/computational costs and/or lack statistical consistency guarantee for optimizing F-measure at the population level.

The complementarity between SGD and EA is worth investigating.

Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data.

We aim at using a large observational sample and a possibly much smaller experimental sample.

Neural Information Processing Systems http://nips.cc/

To this end, we use algorithms developed in the gradient-based multi-objective optimization literature. These algorithms are not directly applicable to large-scale learning problems since they scale poorly with the dimensionality of the gradients and the number of tasks. We therefore propose an upper bound for the multi-objective loss and show that it can be optimized efficiently. We further prove that optimizing this upper bound yields a Pareto optimal solution under realistic assumptions.