Interpretable Machine Learning Reading Group

This semester (2018 Fall), the Interpretable ML Reading Group meets every Tuesday at 1:00-2:00 pm, in CS 5331. Details will be announced via the mailing list. Below we maintain an archive of past presentations.
Date Title Speaker
10/16/2018 Towards Robust Interpretability with Self-Explaining Neural Networks Xuezhou Zhang
05/10/2018 Probably Approximately Metric-Fair Learning Yifeng Teng
04/13/2018 Learning Adversarially Fair and Transferable Representations Xuezhou Zhang
04/06/2018 Differentiable Abstract Interpretation for Provably Robust Neural Networks Samuel Drews
03/16/2018 Online Learning with an Unknown Fairness Metric Xuezhou Zhang
03/02/2018 Fair Clustering Through Fairlets Yifeng Teng
02/22/2018 Detecting Bias in Black-Box Models Using Transparent Model Distillation Xuezhou Zhang
11/15/2017 Interpreting Classifiers through Attribute Interactions in Datasets Samuel Drews
11/01/2017 A Convex Framework for Fair Regression Yifeng Teng
10/25/2017 On Fairness and Calibration David Merrell
10/18/2017 Decoupled classifiers for fair and efficient machine learning Xuezhou Zhang
10/11/2017 Counterfactual Fairness Group Discussion
10/04/2017 Avoiding Discrimination through Causal Reasoning Group Discussion
09/27/2017 Algorithmic Transparency via Quantitative Input Influence Samuel Drews
09/20/2017 Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings Yingyu Liang
08/23/2017 Proxy Discrimination in Data-Driven Systems Aws Albarghouthi
08/16/2017 Algorithmic decision making and the cost of fairness Yifeng Teng
08/09/2017 Fairness in Reinforcement Learning David Merrell
08/02/2017 Equality of Opportunity in Supervised Learning Xuezhou Zhang