Max-affine regression via first-order methods

by   Seonho Kim, et al.

We consider regression of a max-affine model that produces a piecewise linear model by combining affine models via the max function. The max-affine model ubiquitously arises in applications in signal processing and statistics including multiclass classification, auction problems, and convex regression. It also generalizes phase retrieval and learning rectifier linear unit activation functions. We present a non-asymptotic convergence analysis of gradient descent (GD) and mini-batch stochastic gradient descent (SGD) for max-affine regression when the model is observed at random locations following the sub-Gaussianity and an anti-concentration with additive sub-Gaussian noise. Under these assumptions, a suitably initialized GD and SGD converge linearly to a neighborhood of the ground truth specified by the corresponding error bound. We provide numerical results that corroborate the theoretical finding. Importantly, SGD not only converges faster in run time with fewer observations than alternating minimization and GD in the noiseless scenario but also outperforms them in low-sample scenarios with noise.


page 16

page 17


Acceleration of stochastic gradient descent with momentum by averaging: finite-sample rates and asymptotic normality

Stochastic gradient descent with momentum (SGDM) has been widely used in...

Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation

Max-affine regression refers to a model where the unknown regression fun...

Stochastic Gradient Descent Meets Distribution Regression

Stochastic gradient descent (SGD) provides a simple and efficient way to...

Global Convergence and Stability of Stochastic Gradient Descent

In machine learning, stochastic gradient descent (SGD) is widely deploye...

Shape Matters: Understanding the Implicit Bias of the Noise Covariance

The noise in stochastic gradient descent (SGD) provides a crucial implic...

Online Robust Regression via SGD on the l1 loss

We consider the robust linear regression problem in the online setting w...

Please sign up or login with your details

Forgot password? Click here to reset