arXiv subjects

Wenqian Xing

Publications and source records attributed to Wenqian Xing.

5 recordsLinked to original sources

arXiv2026

Attention Limited Reward Learning

Pairwise human comparisons are a primary interface through which modern AI systems learn human preferences. RLHF and related alignment pipelines typically model such comparisons with Bradley--Terry log-odds, where choice probabilities are governed by latent reward differences. This paper examines what this assumption misses through a reduced-form model motivated by rational inattention, in which each label is generated by a low-capacity evaluation channel. The model separates two forms of ambiguity that standard reward modeling tends to conflate: a comparison may be difficult because the two candidates are genuinely close in value, or because the relevant distinction is hard to detect under limited attention. We show that limited attention can fundamentally distort what pairwise comparisons reveal. In particular, passive comparison data cannot generally distinguish reward, attention, and default tendencies, and heterogeneous attention can make standard Bradley--Terry reward modeling recover misleading rankings. Our analysis shows that learning is governed not by the raw number of labels, but by the amount of attended information each label carries. A case study on human votes over language-model pairs from Chatbot Arena exhibits the predicted signature, a cyclic component of the comparison data that exceeds sampling noise and that no scalar reward can represent; a second case study on perceptual comparisons shows that response times and gaze carry gap information that the labels do not. This perspective suggests that human feedback should be treated not as direct revealed preference, but as an attention-limited measurement process: a weak preference signal may reflect hidden evaluation difficulty rather than genuine indifference.

cs.AI↗

arXiv2025

Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient Estimator

Randomized experiments (or A/B tests) are widely used to evaluate interventions in dynamic systems such as recommendation platforms, marketplaces, and digital health. In these settings, interventions affect both current and future system states, so estimating the global average treatment effect (GATE) requires accounting for temporal dynamics, which is especially challenging in the presence of nonstationarity; existing approaches suffer from high bias, high variance, or both. In this paper, we address this challenge via the novel Truncated Policy Gradient (TPG) estimator, which replaces instantaneous outcomes with short-horizon outcome trajectories. The estimator admits a policy gradient interpretation: it is a truncation of the first-order approximation to the GATE, yielding provable reductions in bias and variance in nonstationary Markovian settings. We further establish a central limit theorem for the TPG estimator and develop a consistent variance estimator that remains valid under nonstationarity with single-trajectory data. We validate our theory with two real-world case studies. The results show that relative to existing approaches, a well-calibrated TPG estimator can achieve a favorable balance between bias and variance in nonstationary settings, highlighting the value of the policy-gradient perspective for designing effective estimators under complex dynamics.

stat.ME↗

arXiv2025

Optimizing Server Locations in Spatial Queues: Parametric and Nonparametric Bayesian Optimization

This paper presents a new model for solving the optimal server location problem in a spatial hypercube queueing model. Unlike deterministic location models, our approach accounts for server availability, varying utilization levels, and dependencies across servers. We prove that the problem is NP-hard and establish lower and upper bounds, as well as asymptotic results, by relating it to special cases of the classical $p$-Median problem. To address the computational challenge, we propose two Bayesian optimization approaches: (i) a parametric approach based on a sparse Bayesian linear model with second-order interactions, and (ii) a nonparametric approach using a Gaussian process surrogate with the $p$-Median objective as the prior mean function. We prove that both methods achieve sublinear regret and converge to the optimal solution. Numerical experiments and a case study using real-world data from the St. Paul, Minnesota, emergency response system show that our approaches consistently identify optimal solutions and outperform all baseline methods.

math.OC↗

arXiv2025

Black-Box Optimization with Implicit Constraints for Public Policy

Black-box optimization (BBO) has become increasingly relevant for tackling complex decision-making problems, especially in public policy domains such as police redistricting. However, its broader application in public policymaking is hindered by the complexity of defining feasible regions and the high-dimensionality of decisions. This paper introduces a novel BBO framework, termed as the Conditional And Generative Black-box Optimization (CageBO). This approach leverages a conditional variational autoencoder to learn the distribution of feasible decisions, enabling a two-way mapping between the original decision space and a simplified, constraint-free latent space. The CageBO efficiently handles the implicit constraints often found in public policy applications, allowing for optimization in the latent space while evaluating objectives in the original space. We validate our method through a case study on large-scale police redistricting problems in Atlanta, Georgia. Our results reveal that our CageBO offers notable improvements in performance and efficiency compared to the baselines.

stat.ML↗

arXiv2023

Generalized Hypercube Queueing Models with Overlapping Service Regions

Motivated by the operations of the Atlanta Police Department, where heavy workloads and staffing shortages increasingly require units to patrol across overlapping service regions, we develop a generalized hypercube queueing model, extending Larson (1974), for spatial service systems with overlapping coverage. Designing effective service regions requires capturing both workload and the operations of mobile servers such as police units. The classical hypercube model, which tracks only whether each server is busy or idle, is well suited to light traffic but inadequate for congested systems with server-specific queues and restricted service regions. We model the system as a Markov chain on a nonnegative integer-valued state space and develop a sparse truncated hyperlattice approximation for efficient steady-state computation and performance evaluation. We further characterize the workloads attainable under stable dispatch policies, establish conditions for stabilizability, and identify dispatch policies that optimally balance workloads. We validate the model through simulation and apply it to the Atlanta Police Department, where rising workloads, staffing shortages, and boundary effects create significant operational challenges. Using real 911 calls-for-service data, our analysis indicates that a police operations system with permitted overlapping patrols can significantly mitigate these problems, leading to more effective deployment of the police force. Although the paper focuses on police districting applications, the generalized hypercube queueing model is applicable to other mobile server models in the general setup.

math.PR↗