arXiv subjects

Chengchun Shi

Publications and source records attributed to Chengchun Shi.

At least 55 records · Page 3Linked to original sources

arXiv2025

Deep Distributional Learning with Non-crossing Quantile Network

In this paper, we introduce a non-crossing quantile (NQ) network for conditional distribution learning. By leveraging non-negative activation functions, the NQ network ensures that the learned distributions remain monotonic, effectively addressing the issue of quantile crossing. Furthermore, the NQ network-based deep distributional learning framework is highly adaptable, applicable to a wide range of applications, from classical non-parametric quantile regression to more advanced tasks such as causal effect estimation and distributional reinforcement learning (RL). We also develop a comprehensive theoretical foundation for the deep NQ estimator and its application to distributional RL, providing an in-depth analysis that demonstrates its effectiveness across these domains. Our experimental results further highlight the robustness and versatility of the NQ network.

stat.ML↗

arXiv2025

Doubly Inhomogeneous Reinforcement Learning

This paper studies reinforcement learning (RL) in doubly inhomogeneous environments under temporal non-stationarity and subject heterogeneity. In a number of applications, it is commonplace to encounter datasets generated by system dynamics that may change over time and population, challenging high-quality sequential decision making. Nonetheless, most existing RL solutions require either temporal stationarity or subject homogeneity, which would result in sub-optimal policies if both assumptions were violated. To address both challenges simultaneously, we propose an original algorithm to determine the ``best data chunks" that display similar dynamics over time and across individuals for policy learning, which alternates between most recent change point detection and cluster identification. Our method is general, and works with a wide range of clustering and change point detection algorithms. It is multiply robust in the sense that it takes multiple initial estimators as input and only requires one of them to be consistent. Moreover, by borrowing information over time and population, it allows us to detect weaker signals and has better convergence properties when compared to applying the clustering algorithm per time or the change point detection algorithm per subject. Empirically, we demonstrate the usefulness of our method through extensive simulations and a real data application.

stat.ML↗

arXiv2025

Off-policy Evaluation with Deeply-abstracted States

Off-policy evaluation (OPE) is crucial for assessing a target policy's impact offline before its deployment. However, achieving accurate OPE in large state spaces remains challenging. This paper studies state abstractions -- originally designed for policy learning -- in the context of OPE. Our contributions are three-fold: (i) We define a set of irrelevance conditions central to learning state abstractions for OPE, and derive a backward-model-irrelevance condition for achieving irrelevance in %sequential and (marginalized) importance sampling ratios by constructing a time-reversed Markov decision process (MDP). (ii) We propose a novel iterative procedure that sequentially projects the original state space into a smaller space, resulting in a deeply-abstracted state, which substantially simplifies the sample complexity of OPE arising from high cardinality. (iii) We prove the Fisher consistencies of various OPE estimators when applied to our proposed abstract state spaces.

stat.ML↗

arXiv2025

Multivariate Dynamic Mediation Analysis under a Reinforcement Learning Framework

Mediation analysis is an important analytic tool commonly used in a broad range of scientific applications. In this article, we study the problem of mediation analysis when there are multivariate and conditionally dependent mediators, and when the variables are observed over multiple time points. The problem is challenging, because the effect of a mediator involves not only the path from the treatment to this mediator itself at the current time point, but also all possible paths pointed to this mediator from its upstream mediators, as well as the carryover effects from all previous time points. We propose a novel multivariate dynamic mediation analysis approach. Drawing inspiration from the Markov decision process model that is frequently employed in reinforcement learning, we introduce a Markov mediation process paired with a system of time-varying linear structural equation models to formulate the problem. We then formally define the individual mediation effect, built upon the idea of simultaneous interventions and intervention calculus. We next derive the closed-form expression and propose an iterative estimation procedure under the Markov mediation process model. We study both the asymptotic property and the empirical performance of the proposed estimator, and further illustrate our method with a mobile health application.

stat.ME↗

arXiv2025

Counterfactually Fair Reinforcement Learning via Sequential Data Preprocessing

When applied in healthcare, reinforcement learning (RL) seeks to dynamically match the right interventions to subjects to maximize population benefit. However, the learned policy may disproportionately allocate efficacious actions to one subpopulation, creating or exacerbating disparities in other socioeconomically-disadvantaged subgroups. These biases tend to occur in multi-stage decision making and can be self-perpetuating, which if unaccounted for could cause serious unintended consequences that limit access to care or treatment benefit. Counterfactual fairness (CF) offers a promising statistical tool grounded in causal inference to formulate and study fairness. In this paper, we propose a general framework for fair sequential decision making. We theoretically characterize the optimal CF policy and prove its stationarity, which greatly simplifies the search for optimal CF policies by leveraging existing RL algorithms. The theory also motivates a sequential data preprocessing algorithm to achieve CF decision making under an additive noise assumption. We prove and then validate our policy learning approach in controlling unfairness and attaining optimal value through simulations. Analysis of a digital health dataset designed to reduce opioid misuse shows that our proposal greatly enhances fair access to counseling.

stat.ML↗

arXiv2025

ARMA-Design: Optimal Treatment Allocation Strategies for A/B Testing in Partially Observable Time Series Experiments

Online experiments %in which experimental units receive a sequence of treatments over time are frequently employed in many technological companies to evaluate the performance of a newly developed policy, product, or treatment relative to a baseline control. In many applications, the experimental units receive a sequence of treatments over time. To handle these time-dependent settings, existing A/B testing solutions typically assume a fully observable experimental environment that satisfies the Markov condition. However, this assumption often does not hold in practice. This paper studies the optimal design for A/B testing in partially observable online experiments. We introduce a controlled (vector) autoregressive moving average model to capture partial observability. We introduce a small signal asymptotic framework to simplify the calculation of asymptotic mean squared errors of average treatment effect estimators under various designs. We develop two algorithms to estimate the optimal design: one utilizing constrained optimization and the other employing reinforcement learning. We demonstrate the superior performance of our designs using two dispatch simulators that realistically mimic the behaviors of drivers and passengers to create virtual environments, along with two real datasets from a ride-sharing company. A Python implementation of our proposal is available at https://github.com/datake/ARMADesign.

econ.EM↗

arXiv2025

Testing Stationarity and Change Point Detection in Reinforcement Learning

We consider offline reinforcement learning (RL) methods in possibly nonstationary environments. Many existing RL algorithms in the literature rely on the stationarity assumption that requires the system transition and the reward function to be constant over time. However, the stationarity assumption is restrictive in practice and is likely to be violated in a number of applications, including traffic signal control, robotics and mobile health. In this paper, we develop a consistent procedure to test the nonstationarity of the optimal Q-function based on pre-collected historical data, without additional online data collection. Based on the proposed test, we further develop a sequential change point detection method that can be naturally coupled with existing state-of-the-art RL methods for policy optimization in nonstationary environments. The usefulness of our method is illustrated by theoretical results, simulation studies, and a real data example from the 2018 Intern Health Study. A Python implementation of the proposed procedure is available at https://github.com/limengbinggz/CUSUM-RL.

stat.ML↗

arXiv2024

Dual Active Learning for Reinforcement Learning from Human Feedback

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in RLHF is to learn the reward function from human feedback. However, human feedback is costly and time-consuming, making it essential to collect high-quality conversation data for human teachers to label. Additionally, different human teachers have different levels of expertise. It is thus critical to query the most appropriate teacher for their opinions. In this paper, we use offline reinforcement learning (RL) to formulate the alignment problem. Motivated by the idea of $D$-optimal design, we first propose a dual active reward learning algorithm for the simultaneous selection of conversations and teachers. Next, we apply pessimistic RL to solve the alignment problem, based on the learned reward estimator. Theoretically, we show that the reward estimator obtained through our proposed adaptive selection strategy achieves minimal generalized variance asymptotically, and prove that the sub-optimality of our pessimistic policy scales as $O(1/\sqrt{T})$ with a given sample budget $T$. Through simulations and experiments on LLMs, we demonstrate the effectiveness of our algorithm and its superiority over state-of-the-arts.

stat.ML↗

arXiv2024

Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning

This paper studies off-policy evaluation (OPE) in the presence of unmeasured confounders. Inspired by the two-way fixed effects regression model widely used in the panel data literature, we propose a two-way unmeasured confounding assumption to model the system dynamics in causal reinforcement learning and develop a two-way deconfounder algorithm that devises a neural tensor network to simultaneously learn both the unmeasured confounders and the system dynamics, based on which a model-based estimator can be constructed for consistent policy value estimation. We illustrate the effectiveness of the proposed estimator through theoretical results and numerical experiments.

cs.LG↗

arXiv2024

Off-policy Evaluation in Doubly Inhomogeneous Environments

This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities", we propose a class of latent factor models for the reward and observation transition functions, under which we develop a general OPE framework that consists of both model-based and model-free approaches. To our knowledge, this is the first paper that develops statistically sound OPE methods in offline RL with double inhomogeneities. It contributes to a deeper understanding of OPE in environments, where standard RL assumptions are not met, and provides several practical approaches in these settings. We establish the theoretical properties of the proposed value estimators and empirically show that our approach outperforms competing methods that ignore either temporal nonstationarity or individual heterogeneity. Finally, we illustrate our method on a data set from the Medical Information Mart for Intensive Care.

stat.ME↗

arXiv2024

Sequential Knockoffs for Variable Selection in Reinforcement Learning

In real-world applications of reinforcement learning, it is often challenging to obtain a state representation that is parsimonious and satisfies the Markov property without prior knowledge. Consequently, it is common practice to construct a state larger than necessary, e.g., by concatenating measurements over contiguous time points. However, needlessly increasing the dimension of the state may slow learning and obfuscate the learned policy. We introduce the notion of a minimal sufficient state in a Markov decision process (MDP) as the subvector of the original state under which the process remains an MDP and shares the same reward function as the original process. We propose a novel SEquEntial Knockoffs (SEEK) algorithm that estimates the minimal sufficient state in a system with high-dimensional complex nonlinear dynamics. In large samples, the proposed method achieves selection consistency. As the method is agnostic to the reinforcement learning algorithm being applied, it benefits downstream tasks such as policy learning. Empirical experiments verify theoretical results and show the proposed approach outperforms several competing methods regarding variable selection accuracy and regret.

stat.ML↗

arXiv2024

Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences

Off-policy evaluation (OPE) is widely applied in sectors such as pharmaceuticals and e-commerce to evaluate the efficacy of novel products or policies from offline datasets. This paper introduces a causal deepset framework that relaxes several key structural assumptions, primarily the mean-field assumption, prevalent in existing OPE methodologies that handle spatio-temporal interference. These traditional assumptions frequently prove inadequate in real-world settings, thereby restricting the capability of current OPE methods to effectively address complex interference effects. In response, we advocate for the implementation of the permutation invariance (PI) assumption. This innovative approach enables the data-driven, adaptive learning of the mean-field function, offering a more flexible estimation method beyond conventional averaging. Furthermore, we present novel algorithms that incorporate the PI assumption into OPE and thoroughly examine their theoretical foundations. Our numerical analyses demonstrate that this novel approach yields significantly more precise estimations than existing baseline algorithms, thereby substantially improving the practical applicability and effectiveness of OPE methodologies. A Python implementation of our proposed method is available at https://github.com/BIG-S2/Causal-Deepsets.

stat.ML↗

arXiv2024

Combining Experimental and Historical Data for Policy Evaluation

This paper studies policy evaluation with multiple data sources, especially in scenarios that involve one experimental dataset with two arms, complemented by a historical dataset generated under a single control arm. We propose novel data integration methods that linearly integrate base policy value estimators constructed based on the experimental and historical data, with weights optimized to minimize the mean square error (MSE) of the resulting combined estimator. We further apply the pessimistic principle to obtain more robust estimators, and extend these developments to sequential decision making. Theoretically, we establish non-asymptotic error bounds for the MSEs of our proposed estimators, and derive their oracle, efficiency and robustness properties across a broad spectrum of reward shift scenarios. Numerical experiments and real-data-based analyses from a ridesharing company demonstrate the superior performance of the proposed estimators.

stat.ML↗

arXiv2024

Robust Offline Reinforcement learning with Heavy-Tailed Rewards

This paper endeavors to augment the robustness of offline reinforcement learning (RL) in scenarios laden with heavy-tailed rewards, a prevalent circumstance in real-world applications. We propose two algorithmic frameworks, ROAM and ROOM, for robust off-policy evaluation and offline policy optimization (OPO), respectively. Central to our frameworks is the strategic incorporation of the median-of-means method with offline RL, enabling straightforward uncertainty estimation for the value function estimator. This not only adheres to the principle of pessimism in OPO but also adeptly manages heavy-tailed rewards. Theoretical results and extensive experiments demonstrate that our two frameworks outperform existing methods on the logged dataset exhibits heavy-tailed reward distributions. The implementation of the proposal is available at https://github.com/Mamba413/ROOM.

cs.LG↗

arXiv2024

Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data

In real-world scenarios, datasets collected from randomized experiments are often constrained by size, due to limitations in time and budget. As a result, leveraging large observational datasets becomes a more attractive option for achieving high-quality policy learning. However, most existing offline reinforcement learning (RL) methods depend on two key assumptions--unconfoundedness and positivity--which frequently do not hold in observational data contexts. Recognizing these challenges, we propose a novel policy learning algorithm, PESsimistic CAusal Learning (PESCAL). We utilize the mediator variable based on front-door criterion to remove the confounding bias; additionally, we adopt the pessimistic principle to address the distributional shift between the action distributions induced by candidate policies, and the behavior policy that generates the observational data. Our key observation is that, by incorporating auxiliary variables that mediate the effect of actions on system dynamics, it is sufficient to learn a lower bound of the mediator distribution function, instead of the Q-function, to partially mitigate the issue of distributional shift. This insight significantly simplifies our algorithm, by circumventing the challenging task of sequential uncertainty quantification for the estimated Q-function. Moreover, we provide theoretical guarantees for the algorithms we propose, and demonstrate their efficacy through simulations, as well as real-world experiments utilizing offline datasets from a leading ride-hailing platform.

stat.ML↗

arXiv2024

Semi-supervised Batch Learning From Logged Data

Off-policy learning methods are intended to learn a policy from logged data, which includes context, action, and feedback (cost or reward) for each sample point. In this work, we build on the counterfactual risk minimization framework, which also assumes access to propensity scores. We propose learning methods for problems where feedback is missing for some samples, so there are samples with feedback and samples missing-feedback in the logged data. We refer to this type of learning as semi-supervised batch learning from logged data, which arises in a wide range of application domains. We derive a novel upper bound for the true risk under the inverse propensity score estimator to address this kind of learning problem. Using this bound, we propose a regularized semi-supervised batch learning method with logged data where the regularization term is feedback-independent and, as a result, can be evaluated using the logged missing-feedback data. Consequently, even though feedback is only present for some samples, a learning policy can be learned by leveraging the missing-feedback samples. The results of experiments derived from benchmark datasets indicate that these algorithms achieve policies with better performance in comparison with logging policies.

cs.LG↗

arXiv2024

On Efficient Inference of Causal Effects with Multiple Mediators

This paper provides robust estimators and efficient inference of causal effects involving multiple interacting mediators. Most existing works either impose a linear model assumption among the mediators or are restricted to handle conditionally independent mediators given the exposure. To overcome these limitations, we define causal and individual mediation effects in a general setting, and employ a semiparametric framework to develop quadruply robust estimators for these causal effects. We further establish the asymptotic normality of the proposed estimators and prove their local semiparametric efficiencies. The proposed method is empirically validated via simulated and real datasets concerning psychiatric disorders in trauma survivors.

stat.ME↗

arXiv2023

Policy Evaluation for Temporal and/or Spatial Dependent Experiments

The aim of this paper is to establish a causal link between the policies implemented by technology companies and the outcomes they yield within intricate temporal and/or spatial dependent experiments. We propose a novel temporal/spatio-temporal Varying Coefficient Decision Process (VCDP) model, capable of effectively capturing the evolving treatment effects in situations characterized by temporal and/or spatial dependence. Our methodology encompasses the decomposition of the Average Treatment Effect (ATE) into the Direct Effect (DE) and the Indirect Effect (IE). We subsequently devise comprehensive procedures for estimating and making inferences about both DE and IE. Additionally, we provide a rigorous analysis of the statistical properties of these procedures, such as asymptotic power. To substantiate the effectiveness of our approach, we carry out extensive simulations and real data analyses.

stat.ME↗