Bandits for Learning to Explain from Explanations

02/07/2021
by   Freya Behrens, et al.
0

We introduce Explearn, an online algorithm that learns to jointly output predictions and explanations for those predictions. Explearn leverages Gaussian Processes (GP)-based contextual bandits. This brings two key benefits. First, GPs naturally capture different kinds of explanations and enable the system designer to control how explanations generalize across the space by virtue of choosing a suitable kernel. Second, Explearn builds on recent results in contextual bandits which guarantee convergence with high probability. Our initial experiments hint at the promise of the approach.

READ FULL TEXT
01/30/2018

The Intriguing Properties of Model Explanations

Linear approximations to the decision boundary of a complex model have b...
12/05/2017

Gaussian Process bandits with adaptive discretization

In this paper, the problem of maximizing a black-box function f:X→R is s...
09/26/2013

Finite-Time Analysis of Kernelised Contextual Bandits

We tackle the problem of online reward maximisation over a large finite ...
02/12/2018

Policy Gradients for Contextual Bandits

We study a generalized contextual-bandits problem, where there is a stat...
06/10/2020

Efficient Contextual Bandits with Continuous Actions

We create a computationally tractable algorithm for contextual bandits w...
04/11/2017

Interpretable Explanations of Black Boxes by Meaningful Perturbation

As machine learning algorithms are increasingly applied to high impact y...
02/28/2017

Stacked Thompson Bandits

We introduce Stacked Thompson Bandits (STB) for efficiently generating p...