DeepAI AI Chat
Log In Sign Up

Debiasing Stochastic Gradient Descent to handle missing values

by   Aude Sportisse, et al.

A major caveat of large scale data is their incom-pleteness. We propose an averaged stochastic gradient algorithm handling missing values in linear models. This approach has the merit to be free from the need of any data distribution modeling and to account for heterogeneous missing proportion. In both streaming and finite-sample settings, we prove that this algorithm achieves convergence rate of O(1 n) at the iteration n, the same as without missing values. We show the convergence behavior and the relevance of the algorithm not only on synthetic data but also on real data sets, including those collected from medical register.


page 1

page 2

page 3

page 4


Trading-off variance and complexity in stochastic gradient descent

Stochastic gradient descent is the method of choice for large-scale mach...

A Model Parallel Proximal Stochastic Gradient Algorithm for Partially Asynchronous Systems

Large models are prevalent in modern machine learning scenarios, includi...

Streaming regularization parameter selection via stochastic gradient descent

We propose a framework to perform streaming covariance selection. Our ap...

Online Dual Coordinate Ascent Learning

The stochastic dual coordinate-ascent (S-DCA) technique is a useful alte...

Convergence of online k-means

We prove asymptotic convergence for a general class of k-means algorithm...

Minimax rate of consistency for linear models with missing values

Missing values arise in most real-world data sets due to the aggregation...

Solving A System Of Linear Equations By Randomized Orthogonal Projections

Randomization has shown catalyzing effects in linear algebra with promis...