A Convex Formulation for Mixed Regression with Two Components: Minimax Optimal Rates

Abstract

We consider the mixed regression problem with two components, under adversarial and stochastic noise. We give a convex optimization formulation that provably recovers the true solution, and provide upper bounds on the recovery errors for both arbitrary noise and stochastic noise settings. We also give matching minimax lower bounds (up to log factors), showing that under certain assumptions, our algorithm is information-theoretically optimal. Our results represent the first tractable algorithm guaranteeing successful recovery with tight bounds on recovery errors and sample complexity.

Added results on minimax lower bounds, which match our upper bounds on recovery errors up to log factors. Appeared in the Conference on Learning Theory (COLT), 2014. (JMLR W&CP 35 :560-604, 2014)

Cited by in corpus (4)

• Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
• Solving Large-scale Systems of Random Quadratic Equations via Stochastic Truncated Amplitude Flow
• A Convex Program for Mixed Linear Regression with a Recovery Guarantee for Well-Separated Data
• Parameter Estimation in Gaussian Mixture Models with Malicious Noise, without Balanced Mixing Coefficients