Uncertainty quantification for distributed regression

05/24/2021
by   Valeriy Avanesov, et al.
0

The ever-growing size of the datasets renders well-studied learning techniques, such as Kernel Ridge Regression, inapplicable, posing a serious computational challenge. Divide-and-conquer is a common remedy, suggesting to split the dataset into disjoint partitions, obtain the local estimates and average them, it allows to scale-up an otherwise ineffective base approach. In the current study we suggest a fully data-driven approach to quantify uncertainty of the averaged estimator. Namely, we construct simultaneous element-wise confidence bands for the predictions yielded by the averaged estimator on a given deterministic prediction set. The novel approach features rigorous theoretical guaranties for a wide class of base learners with Kernel Ridge regression being a special case. As a by-product of our analysis we also obtain a sup-norm consistency result for the divide-and-conquer Kernel Ridge Regression. The simulation study supports the theoretical findings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/22/2013

Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates

We establish optimal convergence rates for a decomposition-based scalabl...
research
07/13/2021

Oversampling Divide-and-conquer for Response-skewed Kernel Ridge Regression

The divide-and-conquer method has been widely used for estimating large-...
research
08/05/2016

Kernel Ridge Regression via Partitioning

In this paper, we investigate a divide and conquer approach to Kernel Ri...
research
03/05/2018

A Comparative Study of Pairwise Learning Methods based on Kernel Ridge Regression

Many machine learning problems can be formulated as predicting labels fo...
research
05/04/2020

Reduced Rank Multivariate Kernel Ridge Regression

In the multivariate regression, also referred to as multi-task learning ...
research
03/23/2019

Measuring the Similarity between Materials with an Emphasis on the Materials Distinctiveness

In this study, we establish a basis for selecting similarity measures wh...
research
09/08/2023

Adaptive Distributed Kernel Ridge Regression: A Feasible Distributed Learning Scheme for Data Silos

Data silos, mainly caused by privacy and interoperability, significantly...

Please sign up or login with your details

Forgot password? Click here to reset