We consider evaluating and training a new policy for the evaluation data by using the historical data obtained from a different policy. The goal of off-policy evaluation (OPE) is to estimate the expected reward of a new policy over the evaluation data, and that of off-policy learning (OPL) is to find a new policy that maximizes the expected reward over the evaluation data. Although the standard OPE and OPL assume the same distribution of covariate between the historical and evaluation data, a covariate shift often exists, i.e., the distribution of the covariate of the historical data is different from that of the evaluation data. In this paper, we derive the efficiency bound of OPE under a covariate shift. Then, we propose doubly robust and efficient estimators for OPE and OPL under a covariate shift by using a nonparametric estimator of the density ratio between the historical and evaluation data distributions. We also discuss other possible estimators and compare their theoretical properties. Finally, we confirm the effectiveness of the proposed estimators through experiments.
We propose a robust regression approach to off-policy evaluation (OPE) for contextual bandits. We frame OPE as a covariate-shift problem and leverage modern robust regression tools. Ours is a general approach that can be used to augment any existing OPE method that utilizes the direct method. When augmenting doubly robust methods, we call the resulting method Triply Robust. We prove upper bounds on the resulting bias and variance, as well as derive novel minimax bounds based on robust minimax analysis for covariate shift. Our robust regression method is compatible with deep learning, and is th…
Beating the Winner's Curse via Inference-Aware Policy Optimization
Operations, Information, and Decisions Department, The Wharton School（沃顿商学院运营、信息与决策部门）；Department of Computer and Information Science, University of Pennsylvania（宾夕法尼亚大学计算机与信息科学系）；Wharton Healthcare Analytics Lab, Wharton AI & Analytics Initiative（沃顿健康分析实验室、沃顿人工智能与分析计划）
We study the problem of policy evaluation and learning from batched contextual bandit data when treatments are continuous, going beyond previous work on discrete treatments. Previous work for discrete treatment/action spaces focuses on inverse probability weighting (IPW) and doubly robust (DR) methods that use a rejection sampling approach for evaluation and the equivalent weighted classification problem for learning. In the continuous setting, this reduction fails as we would almost surely reject all observations. To tackle the case of continuous treatments, we extend the IPW and DR approache…
Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its validity. Traditional measures such as confidence intervals may be insufficient due to noise, limited data and confounding. In this paper we develop a method that could serve as a hybrid human-AI system, to enable human experts to analyze the validity of policy evaluation estimates. This is accomplished by highlighting observations in the data whose removal…
University of Toronto（多伦多大学）；The Hong Kong University of Science and Technology（香港科技大学）
Personalized pricing analytics is becoming an essential tool in retailing. Upon observing the personalized information of each arriving customer, the firm needs to set a price accordingly based on the covariates such as income, education background, past purchasing history to extract more revenue. For new entrants of the business, the lack of historical data may severely limit the power and profitability of personalized pricing. We propose a nonparametric pricing policy to simultaneously learn the preference of customers based on the covariates and maximize the expected revenue over a finite h…
Causal inference explores the causation between actions and the consequent rewards on a covariate set. Recently deep learning has achieved a remarkable performance in causal inference, but existing statistical theories cannot well explain such an empirical success, especially when the covariates are high-dimensional. Most theoretical results in causal inference are asymptotic, suffer from the curse of dimensionality, and only work for the finite-action scenario. To bridge such a gap between theory and practice, this paper studies doubly robust off-policy learning by deep neural networks. When …
Learning covariate importance for matching in policy-relevant observational research
Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA（生物统计学、流行病学与信息学系，宾夕法尼亚大学佩雷尔曼医学学院，费城，PA）；School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China（数据科学学院，香港中文大学（深圳）（CUHK-Shenzhen），中国）
In this paper we revisit the method of off-policy corrections for reinforcement learning (COP-TD) pioneered by Hallak et al. (2017). Under this method, online updates to the value function are reweighted to avoid divergence issues typical of off-policy learning. While Hallak et al.'s solution is appealing, it cannot easily be transferred to nonlinear function approximation. First, it requires a projection step onto the probability simplex; second, even though the operator describing the expected behavior of the off-policy learning algorithm is convergent, it is not known to be a contraction ma…
Université Paris Diderot（巴黎第七大学）；Princeton University（普林斯顿大学）
We consider a multi-armed bandit problem in a setting where each arm produces a noisy reward realization which depends on an observable random covariate. As opposed to the traditional static multi-armed bandit problem, this setting allows for dynamically changing rewards that better describe applications where side information is available. We adopt a nonparametric model where the expected rewards are smooth functions of the covariate and where the hardness of the problem is captured by a margin parameter. To maximize the expected cumulative reward, we introduce a policy called Adaptively Binn…
This chapter covers different approaches to policy evaluation for assessing the causal effect of a treatment or intervention on an outcome of interest. As an introduction to causal inference, the discussion starts with the experimental evaluation of a randomized treatment. It then reviews evaluation methods based on selection on observables (assuming a quasi-random treatment given observed covariates), instrumental variables (inducing a quasi-random shift in the treatment), difference-in-differences and changes-in-changes (exploiting changes in outcomes over time), as well as regression discon…
This paper studies offline Imitation Learning (IL) where an agent learns to imitate an expert demonstrator without additional online environment interactions. Instead, the learner is presented with a static offline dataset of state-action-next state transition triples from a potentially less proficient behavior policy. We introduce Model-based IL from Offline data (MILO): an algorithmic framework that utilizes the static dataset to solve the offline IL problem efficiently both in theory and in practice. In theory, even if the behavior policy is highly sub-optimal compared to the expert, we sho…
An important problem in network analysis is predicting a node attribute using both network covariates, such as graph embedding coordinates or local subgraph counts, and conventional node covariates, such as demographic characteristics. While standard regression methods that make use of both types of covariates may be used for prediction, statistical inference is complicated by the fact that the nodal summary statistics are often dependent in complex ways. We show that under a mild joint exchangeability assumption, a network analog of conformal prediction achieves finite sample validity for a w…
Multi-CATE: Multi-Accurate Conditional Average Treatment Effect Estimation Robust to Unknown Covariate Shifts
Ludwig-Maximilians-University of Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Cornell University（康奈尔大学）；University of Southern California（南加州大学）
Human Technology Institute, The University of Technology Sydney（悉尼科技大学人类技术研究所）；School of Mathematics and Statistics, The University of Sydney（悉尼大学数学与统计学院）；Brain and Mind Centre, The University of Sydney（悉尼大学大脑与心智中心）
Covariate-Elaborated Robust Partial Information Transfer with Conditional Spike-and-Slab Prior
Department of Statistics and Data Science, Fudan University（复旦大学统计与数据科学系）；Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania（宾夕法尼亚大学生物统计学、流行病学与信息学系）；Department of Statistics and Applied Probability, University of California, Santa Barbara（加州大学圣芭芭拉分校统计学与应用概率系）
Committee on Computational and Applied Mathematics, University of Chicago（计算与应用数学委员会，芝加哥大学）；Department of Statistics, University of Chicago（统计学系，芝加哥大学）
Variable selection problem for the nonlinear Cox regression model is considered. In survival analysis, one main objective is to identify the covariates that are associated with the risk of experiencing the event of interest. The Cox proportional hazard model is being used extensively in survival analysis in studying the relationship between survival times and covariates, where the model assumes that the covariate has a log-linear effect on the hazard function. However, this linearity assumption may not be satisfied in practice. In order to extract a representative subset of features, various v…
MIT Economics（麻省理工学院经济学系）；Gatsby Unit, UCL（伦敦大学学院盖茨比研究组）
We propose estimators based on kernel ridge regression for nonparametric causal functions such as dose, heterogeneous, and incremental response curves. Treatment and covariates may be discrete or continuous in general spaces. Due to a decomposition property specific to the RKHS, our estimators have simple closed form solutions. We prove uniform consistency with finite sample rates via original analysis of generalized kernel ridge regression. We extend our main results to counterfactual distributions and to causal functions identified by front and back door criteria. We achieve state-of-the-art…
North Carolina State University（北卡罗来纳州立大学）；London School of Economics and Political Science（伦敦政治经济学院）
Dynamic treatment regimes assign personalized treatments to patients sequentially over time based on their baseline information and time-varying covariates. In mobile health applications, these covariates are typically collected at different frequencies over a long time horizon. In this paper, we propose a deep spectral Q-learning algorithm, which integrates principal component analysis (PCA) with deep Q-learning to handle the mixed frequency data. In theory, we prove that the mean return under the estimated optimal policy converges to that under the optimal one and establish its rate of conve…
We present new methods to estimate causal effects retrospectively from micro data with the assistance of a machine learning ensemble. This approach overcomes two important limitations in conventional methods like regression modeling or matching: (i) ambiguity about the pertinent retrospective counterfactuals and (ii) potential misspecification, overfitting, and otherwise bias-prone or inefficient use of a large identifying covariate set in the estimation of causal effects. Our method targets the analysis toward a well defined ``retrospective intervention effect'' (RIE) based on hypothetical po…
