Filters








35,324 Hits in 7.8 sec

Efficient Online Estimation of Causal Effects by Deciding What to Observe [article]

Shantanu Gupta, Zachary C. Lipton, David Childers
2021 arXiv   pre-print
In this paper, we aim to estimate any functional of a probabilistic model (e.g., a causal effect) as efficiently as possible, by deciding, at each time, which data source to query.  ...  We instantiate our setup for average treatment effect estimation, where structural assumptions are given by a causal graph and data sources may include subsets of mediators, confounders, and instrumental  ...  In this paper, we formalize the sequential problem of deciding, at each time, which data source to query (i.e., what to observe) in order to e ciently estimate a target parameter.  ... 
arXiv:2108.09265v2 fatcat:kiqdgft5wffovp6gr6lhd6bfxq

Machine learning for clinical trials in the era of COVID-19

William R. Zame, Ioana Bica, Cong Shen, Alicia Curth, Hyun-Suk Lee, Stuart Bailey, James Weatherall, David Wright, Frank Bretz, Mihaela van der Schaar
2020 Statistics in Biopharmaceutical Research  
We identify three areas of challenge: ongoing clinical trials for non-COVID-19 drugs, clinical trials for repurposing drugs to treat COVID-19, and clinical trials for new drugs to treat COVID-19.  ...  This article identifies some of those challenges and suggests ways in which machine learning (ML) can help in response to those challenges.  ...  Acknowledgments The authors would like to finish with a huge thank you to all those whose work on the front line of this pandemic is making it possible for us to continue our part of this effort.  ... 
doi:10.1080/19466315.2020.1797867 fatcat:p24xopvftfaqhg6c52fwf4fmba

Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes

Junzhe Zhang, Elias Bareinboim
2019 Neural Information Processing Systems  
A dynamic treatment regime (DTR) consists of a sequence of decision rules, one per stage of intervention, that dictates how to determine the treatment assignment to patients based on evolving treatments  ...  We develop the first adaptive algorithm that achieves near-optimal regret in DTRs in online settings, without any access to historical data.  ...  Acknowledgments This research is supported in parts by grants from IBM Research, Adobe Research, NSF IIS-1704352, and IIS-1750807 (CAREER).  ... 
dblp:conf/nips/ZhangB19 fatcat:mezb5hefbjblth75sh4swfumvq

Causal Reinforcement Learning using Observational and Interventional Data [article]

Maxime Gasse, Damien Grasset, Guillaume Gaudron, Pierre-Yves Oudeyer
2021 arXiv   pre-print
Learning efficiently a causal model of the environment is a key challenge of model-based RL agents operating in POMDPs.  ...  collection of offline experiences, obtained by observing another agent interacting with the environment (observational data).  ...  Acknowledgements We thank David Berger for interesting discussions and for pointing us to relevant bodies of work.  ... 
arXiv:2106.14421v1 fatcat:qtt75zbxbferfeu32n7ttzoh6a

Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning Approach

Junzhe Zhang
2020 International Conference on Machine Learning  
Acknowledgments Zhang and Bareinboim are supported in parts by grants from NSF IIS-1704352 and IIS-1750807 (CAREER).  ...  Online Learning with Causal Bounds We next introduce efficient methods to incorporate the causal bounds into online learning algorithms.  ...  Finally, we introduce efficient methods to accelerate these online learning procedures by leveraging the abundant, yet biased observational (non-experimental) data.  ... 
dblp:conf/icml/Zhang20 fatcat:ugqc6ow4ifeuhh6u22lf4h2tfi

Cutthroat Capitalism versus Cuddly Socialism: Are Americans More Meritocratic and Efficiency-Seeking than Scandinavians?

Ingvild Almås, Alexander W. Cappelen, Bertil Tungodden
2019 Journal of Political Economy  
The study also provides robust causal evidence of fairness considerations being much more fundamental for inequality acceptance than efficiency considerations in both countries.  ...  We show that Americans and Norwegians differ significantly in fairness views, but not in the importance assigned to efficiency.  ...  and the estimated country difference in the causal effect of introducing a cost of redistribution is given by δ C .  ... 
doi:10.1086/705551 fatcat:4vgmi7v4abcxvhpjj76wjzk7nu

Cutthroat Capitalism Versus Cuddly Socialism: Are Americans More Meritocratic and Efficiency-Seeking than Scandinavians?

Ingvild Almås, Alexander Cappelen, Bertil Tungodden
2019 Social Science Research Network  
The study also provides robust causal evidence of fairness considerations being much more fundamental for inequality acceptance than efficiency considerations in both countries.  ...  We show that Americans and Norwegians differ significantly in fairness views, but not in the importance assigned to efficiency.  ...  and the estimated country difference in the causal effect of introducing a cost of redistribution is given by δ C .  ... 
doi:10.2139/ssrn.3343315 fatcat:lpmtveutvrghdmr4tq6wm723fq

Cutthroat Capitalism Versus Cuddly Socialism: Are Americans More Meritocratic and Efficiency-Seeking than Scandinavians?

Ingvild Almms, Alexander W. Cappelen, Bertil Tungodden
2016 Social Science Research Network  
The study also provides robust causal evidence of fairness considerations being much more fundamental for inequality acceptance than efficiency considerations in both countries.  ...  We show that Americans and Norwegians differ significantly in fairness views, but not in the importance assigned to efficiency.  ...  and the estimated country difference in the causal effect of introducing a cost of redistribution is given by δ C .  ... 
doi:10.2139/ssrn.2879358 fatcat:snfkpi4cebd7rn5grntunpuvyy

Differential and Distributional Effects of Energy Efficiency Surveys: Evidence from Electricity Consumption

Galib Rustamov, Thomas J Kniesner
2015 Social Science Research Network  
The objective of this study is to determine whether and to what extent such surveys lead to behavioral changes.  ...  ABSTRACT Differential and Distributional Effects of Energy Efficiency Surveys: Evidence from Electricity Consumption * Our research investigates the magnitude of the effect of residential energy efficiency  ...  The focus for the previous DID method is to produce the average causal effects of program participation.  ... 
doi:10.2139/ssrn.2693352 fatcat:6ncogibawjesvj4wxo4gh7ytve

SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events [article]

Li Xu, He Huang, Jun Liu
2021 arXiv   pre-print
Moreover, we propose Eclipse, a novel Efficient glimpse network via dynamic inference, in order to achieve computation-efficient and reliable video reasoning.  ...  benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios.  ...  This work is supported by SUTD Projects PIE-SGP-Al2020-02 and SRG-ISTD-2020-153.  ... 
arXiv:2103.15538v3 fatcat:jfcpkjriirda7cjwqc6qqrbz74

Data Analytics in Operations Management: A Review [article]

Velibor V. Mišić, Georgia Perakis
2019 arXiv   pre-print
Spurred by the growing availability of data and recent advances in machine learning and optimization methodologies, there has been an increasing application of data analytics to problems in operations  ...  In this paper, we review recent applications of data analytics to operations management, in three major areas -- supply chain management, revenue management and healthcare operations -- and highlight some  ...  Acknowledgments The second author would like to acknowledge the support of NSF grant CMMI-1563343.  ... 
arXiv:1905.00556v1 fatcat:fdjr43du7nacjdxfhw2cyzaovi

A Multi-Platform Study of Crowd Signals Associated with Successful Online Fundraising [article]

Henry K. Dambanemuya, Emőke-Ágnes Horvát
2021 arXiv   pre-print
By applying a multi-method analysis to a study of fundraising in three different online markets, we uncover general crowd dynamics that ultimately decide which projects will succeed.  ...  We rely on a multi-method analysis to investigate the correlates, predictive importance, and quasi-causal effects of features that describe crowd dynamics in determining the success of crowdfunded projects  ...  Acknowledgments This work was supported by the U.S. National Science Foundation under Grant No. IIS-1755873.  ... 
arXiv:2101.06315v1 fatcat:xjvgrtaip5gi3omsn2cwzlthwu

Counterfactual Estimation and Optimization of Click Metrics in Search Engines

Lihong Li, Shunbao Chen, Jim Kleban, Ankur Gupta
2015 Proceedings of the 24th International Conference on World Wide Web - WWW '15 Companion  
This approach effectively allows one to run potentially many online experiments offline from search log, making it possible to estimate and optimize online metrics quickly and inexpensively.  ...  Consequently, it appears impossible to accurately estimate online metrics that depend on user feedback, unless the new engine is actually run to serve live users and compared with a baseline in a controlled  ...  If we run π to choose actions for T rounds and observe the corresponding reward in every round, the value of π can be estimated simply by averaging the observed reward, and this estimate will converge  ... 
doi:10.1145/2740908.2742562 dblp:conf/www/LiCKG15 fatcat:xo5i465tv5cttk2j7tqww4tmta

Causal Models for Real Time Bidding with Repeated User Interactions

Martin Bompaire, Alexandre Gilotte, Benjamin Heymann
2021 Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining  
In this work, we first frame this bidding problem with repeated user interactions by using causal models to value each display individually.  ...  Intuitively, while a user is more likely to make a purchase if the number of displays increases, the marginal effect of each display is expected to be decreasing.  ...  ACKNOWLEDGMENTS We would like to thank Aloïs Bissuel, David Rohde, Eustache Diemert, Flavian Vasile, Guillaume Genthial, Ieva Grublyte, Nicolas Chrysanthos, Olivier Koch and Vincent Grosbois for their  ... 
doi:10.1145/3447548.3467280 fatcat:ormqoi4q2rfvnavcpqlldw665e

Effect of Online Word of Mouth on Product Sales: Focusing on Communication-Channel Characteristics

Jaihyun Jeon, Taewook Lim, Byung-Do Kim, Seok
2019 Asia Marketing Journal  
Moreover, according to the characteristics of communication channels, the effects of online WOM on sales differ.  ...  Our particular aim is to perform an in-depth examination on the effects of communication channel's volume and valence on product sales, two important attributes of online WOM.  ...  decide on estimating the effects from two representative channels simultaneously.  ... 
doi:10.53728/2765-6500.1335 fatcat:hgbxrjv2njepze6fzz6l25rgwq
« Previous Showing results 1 — 15 out of 35,324 results