27 citations · 55 across the 11 of their papers we have counts for
11 papers
Efficient Representation of the Activation Space in Deep Neural Networks
Tanya Akumu, Celia Cintas, Girmaw Abebe Tadesse +3
The representations of the activation space of deep neural networks (DNNs) are widely utilized for tasks like natural language processing, anomaly detection and speech recognition.…
Auditing Predictive Models for Intersectional Biases
Kate S. Boxer, Edward McFowland, Daniel B. Neill
Predictive models that satisfy group fairness criteria in aggregate for members of a protected class, but do not guarantee subgroup fairness, could produce biased predictions for i…
Insufficiently Justified Disparate Impact: A New Criterion for Subgroup Fairness
Neil Menghani, Edward McFowland, Daniel B. Neill
In this paper, we develop a new criterion, "insufficiently justified disparate impact" (IJDI), for assessing whether recommendations (binarized predictions) made by an algorithmic…
EnsembleIV: Creating Instrumental Variables from Ensemble Learners for Robust Statistical Inference with ML-Generated Variables
Gordon Burtch, Edward McFowland, Mochen Yang +1
Despite increasing popularity in empirical studies, the integration of machine learning generated variables into regression models for statistical inference suffers from the measur…
Provable Detection of Propagating Sampling Bias in Prediction Models
Pavan Ravishankar, Qingyu Mo, Edward McFowland +1
With an increased focus on incorporating fairness in machine learning models, it becomes imperative not only to assess and mitigate bias at each stage of the machine learning pipel…
Pattern Detection in the Activation Space for Identifying Synthesized Content
Celia Cintas, Skyler Speakman, Girmaw Abebe Tadesse +3
Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise. The ability to synthesize…
Achieving Reliable Causal Inference with Data-Mined Variables: A Random Forest Approach to the Measurement Error Problem
Mochen Yang, Edward McFowland, Gordon Burtch +1
Combining machine learning with econometric analysis is becoming increasingly prevalent in both research and practice. A common empirical strategy involves the application of predi…
Subset Scanning Over Neural Network Activations
Skyler Speakman, Srihari Sridharan, Sekou Remy +2
This work views neural networks as data generating systems and applies anomalous pattern detection techniques on that data in order to detect when a network is processing an anomal…
Gaussian Process Subset Scanning for Anomalous Pattern Detection in Non-iid Data
William Herlands, Edward McFowland, Andrew Gordon Wilson +1
Identifying anomalous patterns in real-world data is essential for understanding where, when, and how systems deviate from their expected dynamics. Yet methods that separately cons…
Efficient Discovery of Heterogeneous Quantile Treatment Effects in Randomized Experiments via Anomalous Pattern Detection
Edward McFowland, Sriram Somanchi, Daniel B. Neill
In the recent literature on estimating heterogeneous treatment effects, each proposed method makes its own set of restrictive assumptions about the intervention's effects and which…
Estimating Causal Peer Influence in Homophilous Social Networks by Inferring Latent Locations
Edward McFowland, Cosma Rohilla Shalizi
Social influence cannot be identified from purely observational data on social networks, because such influence is generically confounded with latent homophily, i.e., with a node's…