research
∙
10/05/2022
Personalized Decentralized Bilevel Optimization over Stochastic and Directed Networks
While personalization in distributed learning has been extensively studi...
share
research
∙
05/30/2022
Fooling SHAP with Stealthily Biased Sampling
SHAP explanations aim at identifying which features contribute the most ...
research
∙
06/14/2021
Characterizing the risk of fairwashing
Fairwashing refers to the risk that an unfair black-box model can be exp...
research
∙
06/08/2020
Evaluation Criteria for Instance-based Explanation
Explaining predictions made by complex machine learning models helps use...
research
∙
02/10/2020
Interpretable Companions for Black-Box Models
We present an interpretable companion model for any pre-trained black-bo...
research
∙
06/20/2019
Data Cleansing for Models Trained with SGD
Data cleansing is a typical approach used to improve the accuracy of mac...
research
∙
06/05/2019
Enumeration of Distinct Support Vectors for Interactive Decision Making
In conventional prediction tasks, a machine learning algorithm outputs a...
research
∙
01/28/2019
Fairwashing: the risk of rationalization
Black-box explanation is the problem of explaining how a machine learnin...
research
∙
01/24/2019
Pretending Fair Decisions via Stealthily Biased Sampling
Fairness by decision-makers is believed to be auditable by third parties...
research
∙
11/13/2018
Quantile regression approach to conditional mode estimation
In this paper, we consider estimation of the conditional mode of an outc...
research
∙
10/14/2018
Convex Hull Approximation of Nearly Optimal Lasso Solutions
In an ordinary feature selection procedure, a set of important features ...
research
∙
07/12/2018
Maximizing Invariant Data Perturbation with Stochastic Optimization
Feature attribution methods, or saliency maps, are one of the most popul...
research
∙
06/19/2018
Maximally Invariant Data Perturbation as Explanation
While several feature scoring methods are proposed to explain the output...
research
∙
12/23/2017
On Estimation of Conditional Modes Using Multiple Quantile Regressions
We propose an estimation method for the conditional mode when the condit...
research
∙
07/31/2017
Consistent Nonparametric Different-Feature Selection via the Sparsest k-Subgraph Problem
Two-sample feature selection is the problem of finding features that des...
research
∙
11/18/2016
Finding Alternate Features in Lasso
We propose a method for finding alternate features missing in the Lasso ...
research
∙
06/29/2016
Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach
Tree ensembles, such as random forests and boosted trees, are renowned f...
research
∙
06/17/2016
Making Tree Ensembles Interpretable
Tree ensembles, such as random forest and boosted trees, are renowned fo...
research
∙
01/20/2014
Anomaly detection in reconstructed quantum states using a machine-learning technique
The accurate detection of small deviations in given density matrices is ...
research
∙
03/01/2012