Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions

arXiv1907.10154MaRDI QIDQ6322595

Author name not available (Why is that?)

Publication date: 23 July 2019

Abstract: We consider a covariate shift problem where one has access to several different training datasets for the same learning problem and a small validation set which possibly differs from all the individual training distributions. This covariate shift is caused, in part, due to unobserved features in the datasets. The objective, then, is to find the best mixture distribution over the training datasets (with only observed features) such that training a learning algorithm using this mixture has the best validation performance. Our proposed algorithm, $$, combines stochastic gradient descent (SGD) with optimistic tree search and model re-use (evolving partially trained models with samples from different mixture distributions) over the space of mixtures, for this task. We prove simple regret guarantees for our algorithm with respect to recovering the optimal mixture, given a total budget of SGD evaluations. Finally, we validate our algorithm on two real-world datasets.

Has companion code repository: https://github.com/matthewfaw/mixnmatch

This page was built for publication: Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6322595)