每日简报

人类反馈强化学习：通过悲观策略学习动态选择AI 解读

In this paper, we study offline Reinforcement Learning with Human Feedback (RLHF) where we aim to learn the human's underlying reward and the MDP's optimal policy from a set of trajectories induced by human choices. RLHF is challenging for multiple reasons: large state space but limited human feedback, the bounded rationality of human decisions, and the off-policy distribution shift. In this paper, we focus on the Dynamic Discrete Choice (DDC) model for modeling and…

协变量自适应随机化下平均处理效应的半参数有效估计AI 解读

Experiments that use covariate adaptive randomization (CAR) are commonplace in applied economics and other fields. In such experiments, the experimenter first stratifies the sample according to observed baseline covariates and then assigns treatment randomly within these strata so as to achieve balance according to pre-specified stratum-specific target assignment proportions. In this paper, we compute the semiparametric efficiency bound for estimating the average treatment…

时变处理的反事实生成模型AI 解读

Estimating the counterfactual outcome of treatment is essential for decision-making in public health and clinical science, among others. Often, treatments are administered in a sequential, time-varying manner, leading to an exponentially increased number of possible counterfactual outcomes. Furthermore, in modern applications, the outcomes are high-dimensional and conventional average treatment effect estimation fails to capture disparities in individuals. To tackle these…

大规模在线A/B测试中的协变量调整AI 解读

Companies offering web services routinely run randomized online experiments to estimate the causal impact associated with the adoption of new features and policies on key performance metrics of interest. These experiments are used to estimate a variety of effects: the increase in click rate due to the repositioning of a banner, the impact on subscription rate as a consequence of a discount or special offer, etc. In these settings, even effects whose sizes are very small can…

CUTS+：不规则时间序列中的高维因果发现AI 解读

Causal discovery in time-series is a fundamental problem in the machine learning community, enabling causal reasoning and decision-making in complex scenarios. Recently, researchers successfully discover causality by combining neural networks with Granger causality, but their performances degrade largely when encountering high-dimensional data because of the highly redundant network design and huge causal graphs. Moreover, the missing entries in the observations further…

Clip-OGD：序贯实验中自适应 Neyman 分配的实验设计AI 解读

From clinical development of cancer therapies to investigations into partisan bias, adaptive sequential designs have become increasingly popular method for causal inference, as they offer the possibility of improved precision over their non-adaptive counterparts. However, even in simple settings (e.g. two treatments) the extent to which adaptive designs can improve precision is not sufficiently well understood. In this work, we study the problem of Adaptive Neyman Allocation…

含未观测异质性的生产函数识别与估计AI 解读

This paper examines the nonparametric identifiability of production functions, considering firm heterogeneity beyond Hicks-neutral technology terms. We propose a finite mixture model to account for unobserved heterogeneity in production technology and productivity growth processes. Our analysis demonstrates that the production function for each latent type can be nonparametrically identified using four periods of panel data, relying on assumptions similar to those employed…

住宅租金的灵活贝叶斯分位数分析AI 解读

This article develops a random effects quantile regression model for panel data that allows for increased distributional flexibility, multivariate heterogeneity, and time-invariant covariates in situations where mean regression may be unsuitable. Our approach is Bayesian and builds upon the generalized asymmetric Laplace distribution to decouple the modeling of skewness from the quantile parameter. We derive an efficient simulation-based estimation algorithm, demonstrate its…

比利时疫情期间供需冲击传播的动态投入产出模型验证AI 解读

This work validates a dynamic production network model, used to quantify the impact of economic shocks caused by COVID-19 in the UK, using data for Belgium. Because the model was published early during the 2020 COVID-19 pandemic, it relied on several assumptions regarding the magnitude of the observed economic shocks, for which more accurate data have become available in the meantime. We refined the propagated shocks to align with observed data collected during the pandemic…

未测量混杂下观察性研究因果推断的灵活敏感性分析AI 解读

Causal inference with observational studies often suffers from unmeasured confounding, yielding biased estimators based on the unconfoundedness assumption. Sensitivity analysis assesses how the causal conclusions change with respect to different degrees of unmeasured confounding. Most existing sensitivity analysis methods work well for specific types of statistical estimation or testing strategies. We propose a flexible sensitivity analysis framework that can deal with…

因果推断中的双重下降与单调下降：高维合成控制应用AI 解读

Motivated by a recent literature on the double-descent phenomenon in machine learning, we consider highly over-parameterized models in causal inference, including synthetic control with many control units. In such models, there may be so many free parameters that the model fits the training data perfectly. We first investigate high-dimensional linear regression for imputing wage data and estimating average treatment effects, where we find that models with many more…

治疗不依从下因果生存分析的多重稳健估计AI 解读

Comparative effectiveness research frequently addresses a time-to-event outcome and can require unique considerations in the presence of treatment noncompliance. Motivated by the challenges in addressing noncompliance in the ADAPTABLE pragmatic clinical trial, we develop a multiply robust estimator to estimate the principal survival causal effects under the principal ignorability and monotonicity. The multiply robust estimator is consistent even if one, and sometimes two, of…

用双重／去偏机器学习有效估计加权累积治疗效应AI 解读

In empirical studies with time-to-event outcomes, investigators often leverage observational data to conduct causal inference on the effect of exposure when randomized controlled trial data is unavailable. Model misspecification and lack of overlap are common issues in observational studies, and they often lead to inconsistent and inefficient estimators of the average treatment effect. Estimators targeting overlap weighted effects have been proposed to address the challenge…

校正实验中的干扰：抖音案例研究AI 解读

Interference is a ubiquitous problem in experiments conducted on two-sided content marketplaces, such as Douyin (China's analog of TikTok). In many cases, creators are the natural unit of experimentation, but creators interfere with each other through competition for viewers' limited time and attention. "Naive" estimators currently used in practice simply ignore the interference, but in doing so incur bias on the order of the treatment effect. We formalize the problem of…

重复事件数据因果中介分析的稳健推断AI 解读

Recurrent events, including cardiovascular events, are commonly observed in biomedical studies. Researchers must understand the effects of various treatments on recurrent events and investigate the underlying mediation mechanisms by which treatments may reduce the frequency of recurrent events are crucial. Although causal inference methods for recurrent event data have been proposed, they cannot be used to assess mediation. This study proposed a novel methodology of causal…

混合试验中利用外部对照的因果推断框架AI 解读

We consider the challenges associated with causal inference in settings where data from a randomized trial is augmented with control data from an external source to improve efficiency in estimating the average treatment effect (ATE). Through the development of a formal causal inference framework, we outline sufficient causal assumptions about the exchangeability between the internal and external controls to identify the ATE and establish the connection to a novel graphical…

在离散选择模型的深度神经网络中融入领域知识AI 解读

Discrete choice models (DCM) are widely employed in travel demand analysis as a powerful theoretical econometric framework for understanding and predicting choice behaviors. DCMs are formed as random utility models (RUM), with their key advantage of interpretability. However, a core requirement for the estimation of these models is a priori specification of the associated utility functions, making them sensitive to modelers' subjective beliefs. Recently, machine learning…

基于高阶累积量的潜在混杂因果发现AI 解读

Causal discovery with latent confounders is an important but challenging task in many scientific areas. Despite the success of some overcomplete independent component analysis (OICA) based methods in certain domains, they are computationally expensive and can easily get stuck into local optima. We notice that interestingly, by making use of higher-order cumulants, there exists a closed-form solution to OICA in specific cases, e.g., when the mixing procedure follows the…

因果推断入门课程AI 解读

I developed the lecture notes based on my ``Causal Inference'' course at the University of California Berkeley over the past seven years. Since half of the students were undergraduates, my lecture notes only required basic knowledge of probability theory, statistical inference, and linear and logistic regressions.

随机试验中利用历史数据的高效预后调整AI 解读

Although randomized controlled trials (RCTs) are a cornerstone of comparative effectiveness, they typically have much smaller sample size than observational studies because of financial and ethical considerations. Therefore there is interest in using plentiful historical data (either observational data or prior trials) to reduce trial sizes. Previous estimators developed for this purpose rely on unrealistic assumptions, without which the added data can bias the treatment…

关于因果、比较与回归的札记AI 解读

Comparison and contrast are the basic means to unveil causation and learn which treatments work. To build good comparison groups, randomized experimentation is key, yet often infeasible. In such non-experimental settings, we illustrate and discuss diagnostics to assess how well the common linear regression approach to causal inference approximates desirable features of randomized experiments, such as covariate balance, study representativeness, interpolated estimation, and…

最小稀疏性下含高维干扰函数的根号样本量一致半参数学习AI 解读

Treatment effect estimation under unconfoundedness is a fundamental task in causal inference. In response to the challenge of analyzing high-dimensional datasets collected in substantive fields such as epidemiology, genetics, economics, and social sciences, various methods for treatment effect estimation with high-dimensional nuisance parameters (the outcome regression and the propensity score) have been developed in recent years. However, it is still unclear what is the…

连续多时点干预的因果推断AI 解读

There are limited options to estimate the treatment effects of variables which are continuous and measured at multiple time points, particularly if the true dose-response curve should be estimated as closely as possible. However, these situations may be of relevance: in pharmacology, one may be interested in how outcomes of people living with -- and treated for -- HIV, such as viral failure, would vary for time-varying interventions such as different drug concentration…

平衡已观测与未观测协变量的多处理协变量自适应随机化：渐近性质AI 解读

Applications of CAR for balancing continuous covariates remain comparatively rare, especially in multi-treatment clinical trials, and the theoretical properties of multi-treatment CAR have remained largely elusive for decades. In this paper, we consider a general framework of CAR procedures for multi-treatment clinal trials which can balance general covariate features, such as quadratic and interaction terms which can be discrete, continuous, and mixing. We show that under…