Search Results for author:
Found 16 papers, 6 papers with code
Studying Up Public Sector AI: How Networks of Power Relations Shape Agency Decisions Around AI Design and Use
As public sector agencies rapidly introduce new AI tools in high-stakes domains like social services, it becomes critical to understand how decisions to adopt these tools are made in practice.
Predictive Performance Comparison of Decision Policies Under Confounding
However, it is challenging to compare predictive performance against an existing decision-making policy that is generally under-specified and dependent on unobservable factors.
Examining risks of racial biases in NLP tools for child protective services
Given well-established racial bias in this setting, we investigate possible ways deployed NLP is liable to increase racial disparities.
Recentering Validity Considerations through Early-Stage Deliberations Around AI and Policy Design
AI-based decision-making tools are rapidly spreading across a range of real-world, complex domains like healthcare, criminal justice, and child welfare.
Counterfactual Prediction Under Outcome Measurement Error
We also develop a method for estimating treatment-dependent measurement error parameters when these are unknown in advance.
Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making
In this paper, we identify five sources of target variable bias that can impact the validity of proxy labels in human-AI decision-making tasks.
Robust Design and Evaluation of Predictive Algorithms under Unobserved Confounding
Predictive algorithms inform consequential decisions in settings where the outcome is selectively observed given choices made by human decision makers.
The role of the geometric mean in case-control studies
We provide a new definition of collapsibility that makes this choice of aggregation method explicit, and we demonstrate that the odds ratio is collapsible under geometric aggregation.
A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms
Recent research increasingly brings to question the appropriateness of using predictive tools in complex, real-world tasks.
Characterizing Fairness Over the Set of Good Models Under Selective Labels
We develop a framework for characterizing predictive fairness properties over the set of models that deliver similar overall performance, or "the set of good models."
Neural Topic Models with Survival Supervision: Jointly Predicting Time-to-Event Outcomes and Learning How Clinical Features Relate
We present a neural network framework for learning a survival model to predict a time-to-event outcome while simultaneously learning a topic model that reveals feature relationships.
Counterfactual Predictions under Runtime Confounding
We propose a doubly-robust procedure for learning counterfactual prediction models in this setting.
Topic Models with Survival Supervision: Archetypal Analysis and Neural Approaches
The two approaches we propose differ in the generality of topic models they can learn.
Conditional Learning of Fair Representations
We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups in the classification setting.
Counterfactual Risk Assessments, Evaluation, and Fairness
These tools thus reflect risk under the historical policy, rather than under the different decision options that the tool is intended to inform.
Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact
This is the Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact, held in Montreal, Canada on December 8, 2018
