Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity

Eunho Yang, Aurélie C. Lozano
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3911-3920, 2017.

Abstract

Imposing sparse + group-sparse superposition structures in high-dimensional parameter estimation is known to provide flexible regularization that is more realistic for many real-world problems. For example, such a superposition enables partially-shared support sets in multi-task learning, thereby striking the right balance between parameter overlap across tasks and task specificity. Existing theoretical results on estimation consistency, however, are problematic as they require too stringent an assumption: the incoherence between sparse and group-sparse superposed components. In this paper, we fill the gap between the practical success and suboptimal analysis of sparse + group-sparse models, by providing the first consistency results that do not require unrealistic assumptions. We also study non-convex counterparts of sparse + group-sparse models. Interestingly, we show that these are guaranteed to recover the true support set under much milder conditions and with smaller sample size than convex models, which might be critical in practical applications as illustrated by our experiments.

Cite this Paper


BibTeX
@InProceedings{pmlr-v70-yang17g, title = {Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity}, author = {Eunho Yang and Aur{\'e}lie C. Lozano}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {3911--3920}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/yang17g/yang17g.pdf}, url = { http://proceedings.mlr.press/v70/yang17g.html }, abstract = {Imposing sparse + group-sparse superposition structures in high-dimensional parameter estimation is known to provide flexible regularization that is more realistic for many real-world problems. For example, such a superposition enables partially-shared support sets in multi-task learning, thereby striking the right balance between parameter overlap across tasks and task specificity. Existing theoretical results on estimation consistency, however, are problematic as they require too stringent an assumption: the incoherence between sparse and group-sparse superposed components. In this paper, we fill the gap between the practical success and suboptimal analysis of sparse + group-sparse models, by providing the first consistency results that do not require unrealistic assumptions. We also study non-convex counterparts of sparse + group-sparse models. Interestingly, we show that these are guaranteed to recover the true support set under much milder conditions and with smaller sample size than convex models, which might be critical in practical applications as illustrated by our experiments.} }
Endnote
%0 Conference Paper %T Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity %A Eunho Yang %A Aurélie C. Lozano %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-yang17g %I PMLR %P 3911--3920 %U http://proceedings.mlr.press/v70/yang17g.html %V 70 %X Imposing sparse + group-sparse superposition structures in high-dimensional parameter estimation is known to provide flexible regularization that is more realistic for many real-world problems. For example, such a superposition enables partially-shared support sets in multi-task learning, thereby striking the right balance between parameter overlap across tasks and task specificity. Existing theoretical results on estimation consistency, however, are problematic as they require too stringent an assumption: the incoherence between sparse and group-sparse superposed components. In this paper, we fill the gap between the practical success and suboptimal analysis of sparse + group-sparse models, by providing the first consistency results that do not require unrealistic assumptions. We also study non-convex counterparts of sparse + group-sparse models. Interestingly, we show that these are guaranteed to recover the true support set under much milder conditions and with smaller sample size than convex models, which might be critical in practical applications as illustrated by our experiments.
APA
Yang, E. & Lozano, A.C.. (2017). Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:3911-3920 Available from http://proceedings.mlr.press/v70/yang17g.html .

Related Material