Generalization Error of Generalized Linear Models in High Dimensions

Melikasadat Emami, Mojtaba Sahraee-Ardakan, Parthe Pandit, Sundeep Rangan, Alyson Fletcher
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2892-2901, 2020.

Abstract

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our understanding of their generalization capabilities is incomplete and this task is made harder by the non-convexity of the underlying learning problems. We provide a general framework to characterize the asymptotic generalization error for single-layer neural networks (i.e., generalized linear models) with arbitrary non-linearities, making it applicable to regression as well as classification problems. This framework enables analyzing the effect of (i) over-parameterization and non-linearity during modeling; (ii) choices of loss function, initialization, and regularizer during learning; and (iii) mismatch between training and test distributions. As examples, we analyze a few special cases, namely linear regression and logistic regression. We are also able to rigorously and analytically explain the \emph{double descent} phenomenon in generalized linear models.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-emami20a, title = {Generalization Error of Generalized Linear Models in High Dimensions}, author = {Emami, Melikasadat and Sahraee-Ardakan, Mojtaba and Pandit, Parthe and Rangan, Sundeep and Fletcher, Alyson}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {2892--2901}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/emami20a/emami20a.pdf}, url = {https://proceedings.mlr.press/v119/emami20a.html}, abstract = {At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our understanding of their generalization capabilities is incomplete and this task is made harder by the non-convexity of the underlying learning problems. We provide a general framework to characterize the asymptotic generalization error for single-layer neural networks (i.e., generalized linear models) with arbitrary non-linearities, making it applicable to regression as well as classification problems. This framework enables analyzing the effect of (i) over-parameterization and non-linearity during modeling; (ii) choices of loss function, initialization, and regularizer during learning; and (iii) mismatch between training and test distributions. As examples, we analyze a few special cases, namely linear regression and logistic regression. We are also able to rigorously and analytically explain the \emph{double descent} phenomenon in generalized linear models.} }
Endnote
%0 Conference Paper %T Generalization Error of Generalized Linear Models in High Dimensions %A Melikasadat Emami %A Mojtaba Sahraee-Ardakan %A Parthe Pandit %A Sundeep Rangan %A Alyson Fletcher %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-emami20a %I PMLR %P 2892--2901 %U https://proceedings.mlr.press/v119/emami20a.html %V 119 %X At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our understanding of their generalization capabilities is incomplete and this task is made harder by the non-convexity of the underlying learning problems. We provide a general framework to characterize the asymptotic generalization error for single-layer neural networks (i.e., generalized linear models) with arbitrary non-linearities, making it applicable to regression as well as classification problems. This framework enables analyzing the effect of (i) over-parameterization and non-linearity during modeling; (ii) choices of loss function, initialization, and regularizer during learning; and (iii) mismatch between training and test distributions. As examples, we analyze a few special cases, namely linear regression and logistic regression. We are also able to rigorously and analytically explain the \emph{double descent} phenomenon in generalized linear models.
APA
Emami, M., Sahraee-Ardakan, M., Pandit, P., Rangan, S. & Fletcher, A.. (2020). Generalization Error of Generalized Linear Models in High Dimensions. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:2892-2901 Available from https://proceedings.mlr.press/v119/emami20a.html.

Related Material