Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP
arXiv:1706.04690
Abstract
Online sparse linear regression is an online problem where an algorithm repeatedly chooses a subset of coordinates to observe in an adversarially chosen feature vector, makes a real-valued prediction, receives the true label, and incurs the squared loss. The goal is to design an online learning algorithm with sublinear regret to the best sparse linear predictor in hindsight. Without any assumptions, this problem is known to be computationally intractable. In this paper, we make the assumption that data matrix satisfies restricted isometry property, and show that this assumption leads to computationally efficient algorithms with sublinear regret for two variants of the problem. In the first variant, the true label is generated according to a sparse linear model with additive Gaussian noise. In the second, the true label is chosen adversarially.
arXiv commentAppearing in 34th International Conference on Machine Learning (ICML), 2017
References in corpus (6)
- Simultaneous analysis of Lasso and Dantzig selector
- Sparse recovery under matrix uncertainty
- Efficient Learning with Partially Observed Attributes
- Variable Selection is Hard
- Linear Regression with Limited Observation
- Model Selection for High-Dimensional Regression under the Generalized Irrepresentability Condition