← Back to papers
2011 AISTATS AISTATS 2011

Linear-Time Estimators for Propensity Scores

Abstract

We present linear-time estimators for three popular covariate shift correction and propensity scoring algorithms: logistic regression(LR), kernel mean matching(KMM), and maximum entropy mean matching(MEMM). This allows applications in situations where both treatment and control groups are large. We also show that the last two algorithms differ only in their choice of regularizer ($\ell_2$ of the Radon Nikodym derivative vs. maximum entropy). Experiments show that all methods scale well.

🧭 Keyword Pioneer — propensity score
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy
📈 Trend Setter — Domain Adaptation
🐣 Hot Topic Early Bird — logistic regression

Authors

Deepak Agarwal , Lihong Li , Alexander Smola

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Statistical Learning Machine Learning > Application Areas > Domain Adaptation Machine Learning > Learning Types > Domain Adaptation

Keywords

maximum entropy logistic regression covariate shift propensity score kernel mean matching linear-time estimator
Download PDF

Related papers

Tighter Relaxations for MAP-MRF Inference: A Local Primal-Dual Gap based Separation Algorithm 2011
Deep Learners Benefit More from Out-of-Distribution Examples 2011
Bagged Structure Learning of Bayesian Network 2011
Convergent Decomposition Solvers for Tree-reweighted Free Energies 2011
Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization 2011