Learning Mixtures of Linear Classifiers

Abstract

We consider a discriminative learning (regression) problem, whereby the regression function is a convex combination of k linear classifiers. Existing approaches are based on the EM algorithm, or similar techniques, without provable guarantees. We develop a simple method based on spectral techniques and a `mirroring' trick, that discovers the subspace spanned by the classifiers' parameter vectors. Under a probabilistic assumption on the feature vector distribution, we prove that this approach has nearly optimal statistical efficiency.

References in corpus (1)

• Spectral Experts for Estimating Mixtures of Linear Regressions

Cited by in corpus (7)

• Provable Tensor Methods for Learning Mixtures of Generalized Linear Models
• Optimal Subspace Estimation Using Overidentifying Vectors via Generalized Method of Moments
• Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms
• Learning Combinations of Sigmoids Through Gradient Estimation
• Recovery of sparse linear classifiers from mixture of responses
• Learning Mixtures of Sparse Linear Regressions Using Sparse Graph Codes
• Support Recovery of Sparse Signals from a Mixture of Linear Measurements