Himabindu Lakkaraju

is this you? claim profile

0 followers
Harvard University ∙ Stanford University

Towards Robust and Reliable Algorithmic Recourse

As predictive models are increasingly being deployed in high-stakes deci...
02/26/2021 ∙ by Sohini Upadhyay, et al. ∙ 0 ∙ share

read it
Towards a Unified Framework for Fair and Stable Graph Representation Learning

As the representations output by Graph Neural Networks (GNNs) are increa...
02/25/2021 ∙ by Chirag Agarwal, et al. ∙ 16 ∙ share

read it
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

As machine learning black boxes are increasingly being deployed in criti...
02/21/2021 ∙ by Sushant Agarwal, et al. ∙ 10 ∙ share

read it
Can I Still Trust You?: Understanding the Impact of Distribution Shifts on Algorithmic Recourses

As predictive models are being increasingly deployed to make a variety o...
12/22/2020 ∙ by Kaivalya Rawal, et al. ∙ 0 ∙ share

read it
Does Fair Ranking Improve Minority Outcomes? Understanding the Interplay of Human and Algorithmic Biases in Online Hiring

Ranking algorithms are being widely employed in various online hiring pl...
12/01/2020 ∙ by Tom Sühr, et al. ∙ 0 ∙ share

read it
Robust and Stable Black Box Explanations

As machine learning black boxes are increasingly being deployed in real-...
11/12/2020 ∙ by Himabindu Lakkaraju, et al. ∙ 0 ∙ share

read it
When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making

As machine learning (ML) models are increasingly being employed to assis...
11/12/2020 ∙ by Sean McGrath, et al. ∙ 0 ∙ share

read it
Ensuring Actionable Recourse via Adversarial Training

As machine learning models are increasingly deployed in high-stakes doma...
11/12/2020 ∙ by Alexis Ross, et al. ∙ 0 ∙ share

read it
Incorporating Interpretable Output Constraints in Bayesian Neural Networks

Domains where supervised models are deployed often come with task-specif...
10/21/2020 ∙ by Wanqian Yang, et al. ∙ 0 ∙ share

read it
Interpretable and Interactive Summaries of Actionable Recourses

As predictive models are increasingly being deployed in high-stakes deci...
09/15/2020 ∙ by Kaivalya Rawal, et al. ∙ 18 ∙ share

read it
How Much Should I Trust You? Modeling Uncertainty of Black Box Explanations

As local explanations of black box models are increasingly being employe...
08/11/2020 ∙ by Dylan Slack, et al. ∙ 24 ∙ share

read it
Fair Influence Maximization: A Welfare Optimization Approach

Several social interventions (e.g., suicide and HIV prevention) leverage...
06/14/2020 ∙ by Aida Rahmattalabi, et al. ∙ 10 ∙ share

read it
"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations

As machine learning black boxes are increasingly being deployed in criti...
11/15/2019 ∙ by Himabindu Lakkaraju, et al. ∙ 0 ∙ share

read it
How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods

As machine learning black boxes are increasingly being deployed in domai...
11/06/2019 ∙ by Dylan Slack, et al. ∙ 20 ∙ share

read it
Interpretable & Explorable Approximations of Black Box Models

We propose Black Box Explanations through Transparent Approximations (BE...
07/04/2017 ∙ by Himabindu Lakkaraju, et al. ∙ 0 ∙ share

read it
Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration

Predictive models deployed in the real world may assign incorrect labels...
10/28/2016 ∙ by Himabindu Lakkaraju, et al. ∙ 0 ∙ share

read it
Learning Cost-Effective Treatment Regimes using Markov Decision Processes

Decision makers, such as doctors and judges, make crucial decisions such...
10/21/2016 ∙ by Himabindu Lakkaraju, et al. ∙ 0 ∙ share

read it

Himabindu Lakkaraju

Featured Co-authors

Jure Leskovec

Finale Doshi-Velez

Cynthia Rudin

Zhiwei Steven Wu

Sameer Singh

Milind Tambe

Osbert Bastani

Eric Horvitz

Marinka Zitnik

Ece Kamar

Rich Caruana

Towards Robust and Reliable Algorithmic Recourse

Towards a Unified Framework for Fair and Stable Graph Representation Learning

Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

Can I Still Trust You?: Understanding the Impact of Distribution Shifts on Algorithmic Recourses

Does Fair Ranking Improve Minority Outcomes? Understanding the Interplay of Human and Algorithmic Biases in Online Hiring

Robust and Stable Black Box Explanations

When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making

Ensuring Actionable Recourse via Adversarial Training

Incorporating Interpretable Output Constraints in Bayesian Neural Networks

Interpretable and Interactive Summaries of Actionable Recourses

How Much Should I Trust You? Modeling Uncertainty of Black Box Explanations

Fair Influence Maximization: A Welfare Optimization Approach

"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations

How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods

Interpretable & Explorable Approximations of Black Box Models

Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration

Learning Cost-Effective Treatment Regimes using Markov Decision Processes