Linear-Time Estimators for Propensity Scores

Deepak Agarwal, Lihong Li, Alexander Smola
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, PMLR 15:93-100, 2011.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v15-agarwal11c, title = {Linear-Time Estimators for Propensity Scores}, author = {Agarwal, Deepak and Li, Lihong and Smola, Alexander}, booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics}, pages = {93--100}, year = {2011}, editor = {Gordon, Geoffrey and Dunson, David and Dudík, Miroslav}, volume = {15}, series = {Proceedings of Machine Learning Research}, address = {Fort Lauderdale, FL, USA}, month = {11--13 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v15/agarwal11c/agarwal11c.pdf}, url = {https://proceedings.mlr.press/v15/agarwal11c.html}, 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.} }
Endnote
%0 Conference Paper %T Linear-Time Estimators for Propensity Scores %A Deepak Agarwal %A Lihong Li %A Alexander Smola %B Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2011 %E Geoffrey Gordon %E David Dunson %E Miroslav Dudík %F pmlr-v15-agarwal11c %I PMLR %P 93--100 %U https://proceedings.mlr.press/v15/agarwal11c.html %V 15 %X 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.
RIS
TY - CPAPER TI - Linear-Time Estimators for Propensity Scores AU - Deepak Agarwal AU - Lihong Li AU - Alexander Smola BT - Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics DA - 2011/06/14 ED - Geoffrey Gordon ED - David Dunson ED - Miroslav Dudík ID - pmlr-v15-agarwal11c PB - PMLR DP - Proceedings of Machine Learning Research VL - 15 SP - 93 EP - 100 L1 - http://proceedings.mlr.press/v15/agarwal11c/agarwal11c.pdf UR - https://proceedings.mlr.press/v15/agarwal11c.html AB - 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. ER -
APA
Agarwal, D., Li, L. & Smola, A.. (2011). Linear-Time Estimators for Propensity Scores. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 15:93-100 Available from https://proceedings.mlr.press/v15/agarwal11c.html.

Related Material