Search Results for author: Giles Hooker

Found 20 papers, 11 papers with code

S-LIME: Stabilized-LIME for Model Explanation

1 code implementation15 Jun 2021 Zhengze Zhou, Giles Hooker, Fei Wang

An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare.

Generalised Boosted Forests

no code implementations24 Feb 2021 Indrayudh Ghosal, Giles Hooker

We use these residuals and some corresponding weights to fit a base random forest and then repeat the same to obtain a boost random forest.

Bridging Breiman's Brook: From Algorithmic Modeling to Statistical Learning

no code implementations23 Feb 2021 Lucas Mentch, Giles Hooker

In 2001, Leo Breiman wrote of a divide between "data modeling" and "algorithmic modeling" cultures.

$V$-statistics and Variance Estimation

1 code implementation2 Dec 2019 Zhengze Zhou, Lucas Mentch, Giles Hooker

This paper develops a general framework for analyzing asymptotics of $V$-statistics.

Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models

2 code implementations12 Nov 2019 Benjamin Lengerich, Sarah Tan, Chun-Hao Chang, Giles Hooker, Rich Caruana

Models which estimate main effects of individual variables alongside interaction effects have an identifiability challenge: effects can be freely moved between main effects and interaction effects without changing the model prediction.

Additive models

Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importance

1 code implementation1 May 2019 Giles Hooker, Lucas Mentch, Siyu Zhou

This paper reviews and advocates against the use of permute-and-predict (PaP) methods for interpreting black box functions.

Tree Boosted Varying Coefficient Models

1 code implementation1 Apr 2019 Yichen Zhou, Giles Hooker

This paper investigates the integration of gradient boosted decision trees and varying coefficient models.

Methodology

Unbiased Measurement of Feature Importance in Tree-Based Methods

1 code implementation12 Mar 2019 Zhengze Zhou, Giles Hooker

We propose a modification that corrects for split-improvement variable importance measures in Random Forests and other tree-based methods.

Feature Importance

Approximation Trees: Statistical Stability in Model Distillation

no code implementations22 Aug 2018 Yichen Zhou, Zhengze Zhou, Giles Hooker

Here, we consider the use of regression trees as a student model, in which nodes of the tree can be used as `explanations' for particular predictions, and the whole structure of the tree can be used as a global representation of the resulting function.

Boosting Random Forests to Reduce Bias; One-Step Boosted Forest and its Variance Estimate

2 code implementations21 Mar 2018 Indrayudh Ghosal, Giles Hooker

In this paper we propose using the principle of boosting to reduce the bias of a random forest prediction in the regression setting.

Prediction Intervals

Considerations When Learning Additive Explanations for Black-Box Models

no code implementations ICLR 2019 Sarah Tan, Giles Hooker, Paul Koch, Albert Gordo, Rich Caruana

In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based explanations.

Additive models

A Double Parametric Bootstrap Test for Topic Models

no code implementations19 Nov 2017 Skyler Seto, Sarah Tan, Giles Hooker, Martin T. Wells

Non-negative matrix factorization (NMF) is a technique for finding latent representations of data.

Topic Models

Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation

3 code implementations17 Oct 2017 Sarah Tan, Rich Caruana, Giles Hooker, Yin Lou

We compare the student model trained with distillation to a second un-distilled transparent model trained on ground-truth outcomes, and use differences between the two models to gain insight into the black-box model.

Machine Learning and the Future of Realism

no code implementations15 Apr 2017 Giles Hooker, Cliff Hooker

Among the consequences just might be the triumph of anti-realism over realism.

Medical Diagnosis

Bootstrap Bias Corrections for Ensemble Methods

no code implementations1 Jun 2015 Giles Hooker, Lucas Mentch

This paper examines the use of a residual bootstrap for bias correction in machine learning regression methods.

Formal Hypothesis Tests for Additive Structure in Random Forests

no code implementations7 Jun 2014 Lucas Mentch, Giles Hooker

While statistical learning methods have proved powerful tools for predictive modeling, the black-box nature of the models they produce can severely limit their interpretability and the ability to conduct formal inference.

Quantifying Uncertainty in Random Forests via Confidence Intervals and Hypothesis Tests

no code implementations25 Apr 2014 Lucas Mentch, Giles Hooker

Instead of aggregating full bootstrap samples, we consider predicting by averaging over trees built on subsamples of the training set and demonstrate that the resulting estimator takes the form of a U-statistic.

Control Theory and Experimental Design in Diffusion Processes

1 code implementation13 Oct 2012 Giles Hooker, Kevin K. Lin, Bruce Rogers

We propose to accomplish this with a two-step strategy: when the full state vector of the diffusion process is observable continuously, we formulate this as an optimal control problem and apply numerical techniques from stochastic optimal control to solve it.

Methodology

Cannot find the paper you are looking for? You can Submit a new open access paper.