The Shooting Regressor; Randomized Gradient-Based Ensembles

09/14/2020
by   Nicholas Smith, et al.
5

An ensemble method is introduced that utilizes randomization and loss function gradients to compute a prediction. Multiple weakly-correlated estimators approximate the gradient at randomly sampled points on the error surface and are aggregated into a final solution. A scaling parameter is described that controls a trade-off between ensemble correlation and precision. Numerical methods for estimating optimal values of the parameter are described. Empirical results are computed over a popular dataset. Inferential statistics on these results show that the method is capable of outperforming existing techniques in terms of increased accuracy.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

10/25/2018

RELF: Robust Regression Extended with Ensemble Loss Function

Ensemble techniques are powerful approaches that combine several weak le...
03/01/2020

Stein Variational Inference for Discrete Distributions

Gradient-based approximate inference methods, such as Stein variational ...
12/28/2021

Ensemble Recognition in Reproducing Kernel Hilbert Spaces through Aggregated Measurements

In this paper, we study the problem of learning dynamical properties of ...
11/08/2016

The Loss Surface of Residual Networks: Ensembles and the Role of Batch Normalization

Deep Residual Networks present a premium in performance in comparison to...
07/20/2019

Estimating the Algorithmic Variance of Randomized Ensembles via the Bootstrap

Although the methods of bagging and random forests are some of the most ...
03/04/2013

A Sharp Bound on the Computation-Accuracy Tradeoff for Majority Voting Ensembles

When random forests are used for binary classification, an ensemble of t...
06/24/2016

Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles

Many practical perception systems exist within larger processes that inc...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.