Performance Analysis
Does mitigating ML's impact disparity require treatment disparity?
Zachary Lipton, Julian McAuley, Alexandra Chouldechova
Neural Information Processing Systems http://nips.cc/
Empirical Risk Minimization Under Fairness Constraints
Michele Donini, Luca Oneto, Shai Ben-David, John S. Shawe-Taylor, Massimiliano Pontil
We address the problem of algorithmic fairness: ensuring that sensitive information does not unfairly influence the outcome of a classifier. We present an approach based on empirical risk minimization, which incorporates a fairness constraint into the learning problem. It encourages the conditional risk of the learned classifier to be approximately constant with respect to the sensitive variable. We derive both risk and fairness bounds that support the statistical consistency of our methodology. We specify our approach to kernel methods and observe that the fairness requirement implies an orthogonality constraint which can be easily added to these methods. We further observe that for linear models the constraint translates into a simple data preprocessing step. Experiments indicate that the method is empirically effective and performs favorably against state-of-the-art approaches.
A Bandit Approach to Sequential Experimental Design with False Discovery Control
We propose an adaptive sampling approach for multiple testing which aims to maximize statistical power while ensuring anytime false discovery control.
To Trust Or Not To Trust A Classifier
Heinrich Jiang, Been Kim, Melody Guan, Maya Gupta
Knowing when a classifier's prediction can be trusted is useful in many applications
Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization
Xiaoxuan Zhang, Mingrui Liu, Xun Zhou, Tianbao Yang
In this paper, we consider online F-measure optimization (OFO). Unlike traditional performance metrics (e.g., classification error rate), F-measure is non-decomposable over training examples and is a non-convex function of model parameters, making it much more difficult to be optimized in an online fashion. Most existing results of OFO usually suffer from high memory/computational costs and/or lack statistical consistency guarantee for optimizing F-measure at the population level.
Early Stopping for Nonparametric Testing
In this paper, we show that early stopping can also be applied to obtain the minimax optimal testing in a general non-parametric setup.
Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations
Neural Information Processing Systems http://nips.cc/
On preserving non-discrimination when combining expert advice
Avrim Blum, Suriya Gunasekar, Thodoris Lykouris, Nati Srebro
Discrimination is commonly an issue in applications where decisions need to be made sequentially. The most prominent such application is online advertising where platforms need to sequentially select which ad to display in response to particular query searches.
Out-of-Distribution Detection using Multiple Semantic Label Representations
Gabi Shalev, Yossi Adi, Joseph Keshet
Neural Information Processing Systems http://nips.cc/
Why Is My Classifier Discriminatory?
Irene Chen, Fredrik D. Johansson, David Sontag
Recent attempts to achieve fairness in predictive models focus on the balance between fairness and accuracy.