no code implementations • 13 Dec 2023 • Tanya Akumu, Celia Cintas, Girmaw Abebe Tadesse, Adebayo Oshingbesan, Skyler Speakman, Edward McFowland III
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.
no code implementations • 22 Jun 2023 • Kate S. Boxer, Edward McFowland III, 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 individuals at the intersection of two or more protected classes.
no code implementations • 19 Jun 2023 • Neil Menghani, Edward McFowland III, 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 decision support tool are fair.
no code implementations • 6 Mar 2023 • Gordon Burtch, Edward McFowland III, Mochen Yang, Gediminas Adomavicius
Despite increasing popularity in empirical studies, the integration of machine learning generated variables into regression models for statistical inference suffers from the measurement error problem, which can bias estimation and threaten the validity of inferences.
no code implementations • 13 Feb 2023 • Pavan Ravishankar, Qingyu Mo, Edward McFowland III, Daniel B. Neill
We provide a theoretical analysis of how a specific form of data bias, differential sampling bias, propagates from the data stage to the prediction stage.
no code implementations • 26 May 2021 • Celia Cintas, Skyler Speakman, Girmaw Abebe Tadesse, Victor Akinwande, Edward McFowland III, Komminist Weldemariam
Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise.
no code implementations • 19 Dec 2020 • Mochen Yang, Edward McFowland III, Gordon Burtch, Gediminas Adomavicius
The random forest algorithm performs best when comprised of a set of trees that are individually accurate in their predictions, yet which also make 'different' mistakes, i. e., have weakly correlated prediction errors.
no code implementations • ICLR 2020 • Skyler Speakman, Celia Cintas, Victor Akinwande, Srihari Sridharan, Edward McFowland III
This work introduces ``Subset Scanning methods from the anomalous pattern detection domain to the task of detecting anomalous inputs to neural networks.
no code implementations • 4 Apr 2018 • William Herlands, Edward McFowland III, Andrew Gordon Wilson, Daniel B. Neill
We introduce methods for identifying anomalous patterns in non-iid data by combining Gaussian processes with novel log-likelihood ratio statistic and subset scanning techniques.
no code implementations • 24 Mar 2018 • Edward McFowland III, 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 subpopulations to explicitly estimate.