Projective Inference in High-dimensional Problems: Prediction and Feature Selection

by   Juho Piironen, et al.

This paper discusses predictive inference and feature selection for generalized linear models with scarce but high-dimensional data. We argue that in many cases one can benefit from a decision theoretically justified two-stage approach: first, construct a possibly non-sparse model that predicts well, and then find a minimal subset of features that characterize the predictions. The model built in the first step is referred to as the reference model and the operation during the latter step as predictive projection. The key characteristic of this approach is that it finds an excellent tradeoff between sparsity and predictive accuracy, and the gain comes from utilizing all available information including prior and that coming from the left out features. We review several methods that follow this principle and provide novel methodological contributions. We present a new projection technique that unifies two existing techniques and is both accurate and fast to compute. We also propose a way of evaluating the feature selection process using fast leave-one-out cross-validation that allows for easy and intuitive model size selection. Furthermore, we prove a theorem that helps to understand the conditions under which the projective approach could be beneficial. The benefits are illustrated via several simulated and real world examples.


page 1

page 2

page 3

page 4


A Study of Feature Selection and Extraction Algorithms for Cancer Subtype Prediction

In this work, we study and analyze different feature selection algorithm...

Sparsity Regularization and feature selection in large dimensional data

Feature selection has evolved to be an important step in several machine...

Explainable Predictive Modeling for Limited Spectral Data

Feature selection of high-dimensional labeled data with limited observat...

Target-Focused Feature Selection Using a Bayesian Approach

In many real-world scenarios where data is high dimensional, test time a...

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control

Selective rationalization has become a common mechanism to ensure that p...

Robust and efficient projection predictive inference

The concepts of Bayesian prediction, model comparison, and model selecti...

Feature Selection for Vertex Discriminant Analysis

We revisit vertex discriminant analysis (VDA) from the perspective of pr...

Please sign up or login with your details

Forgot password? Click here to reset