arXiv subjects

Huiying Zhong

Publications and source records attributed to Huiying Zhong.

4 recordsLinked to original sources

arXiv2026

Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback

Pluralistic alignment requires learning from feedback that reflects persistent and potentially conflicting stakeholder preferences while ultimately selecting a single collective policy. We study this problem in offline reinforcement learning from human feedback (RLHF), where the party associated with each comparison is observed. Under a shared low-rank linear reward model, we jointly estimate party-specific rewards and perform pessimistic policy optimization under Nash, Utilitarian, and Egalitarian social-welfare objectives. We establish nonasymptotic bounds for party-specific reward estimation and the resulting policy suboptimality under offline coverage conditions. We further consider general pairwise preferences that need not admit a scalar reward representation and may exhibit cycles. In this setting, we construct a pessimistic von Neumann winner policy and derive corresponding performance guarantees. Under these models, our results provide a unified finite-sample solution to a central challenge in pluralistic alignment: learning from limited, heterogeneous, and potentially cyclic feedback, and producing a single policy with explicit collective-welfare guarantees. Our framework thereby makes preference aggregation an explicit and statistically analyzable design choice rather than an implicit consequence of pooling human feedback.

cs.LG↗

arXiv2026

Human-AI Productivity Paradoxes: Modeling the Interplay of Skill, Effort, and AI Assistance

Generative Artificial Intelligence (AI) tools are rapidly adopted in the workplace and in education, yet the empirical evidence on AI's impact remains mixed. We propose a model of human-AI interaction to better understand and analyze several mechanisms by which AI affects productivity. In our setup, human agents with varying skill levels exert utility-maximizing effort to produce certain task outcomes with AI assistance. We find that incorporating either endogeneity in skill development or in AI unreliability can induce a productivity paradox: increased levels of AI assistance may degrade productivity, leading to potentially significant shortfalls. Moreover, we examine the long-term distributional effect of AI on skill, and demonstrate that skill polarization can emerge in steady state when accounting for heterogeneity in AI literacy -- the agent's capability to identify and adapt to inaccurate AI outputs. Our results elucidate several mechanisms that may explain the emergence of human-AI productivity paradoxes and skill polarization, and identify simple measures that characterize when they arise.

cs.GT↗

arXiv2025

Statistical Inference under Performativity

Performativity of predictions refers to the phenomenon where prediction-informed decisions influence the very targets they aim to predict -- a dynamic commonly observed in policy-making, social sciences, and economics. In this paper, we initiate an end-to-end framework of statistical inference under performativity. Our contributions are twofold. First, we establish a central limit theorem for estimation and inference in the performative setting, enabling standard inferential tasks such as constructing confidence intervals and conducting hypothesis tests in policy-making contexts. Second, we leverage this central limit theorem to study prediction-powered inference (PPI) under performativity. This approach yields more precise estimates and tighter confidence regions for the model parameters (i.e., policies) of interest in performative prediction. We validate the effectiveness of our framework through numerical experiments. To the best of our knowledge, this is the first work to establish a complete statistical inference under performativity, introducing new challenges and inference settings that we believe will provide substantial value to policy-making, statistics, and machine learning.

stat.ML↗

arXiv2024

Multi-Layer Kernel Machines: Fast and Optimal Nonparametric Regression with Uncertainty Quantification

Kernel ridge regression (KRR) is widely used for nonparametric regression over reproducing kernel Hilbert spaces. It offers powerful modeling capabilities at the cost of significant computational costs, which typically require $O(n^3)$ computational time and $O(n^2)$ storage space, with the sample size n. We introduce a novel framework of multi-layer kernel machines that approximate KRR by employing a multi-layer structure and random features, and study how the optimal number of random features and layer sizes can be chosen while still preserving the minimax optimality of the approximate KRR estimate. For various classes of random features, including those corresponding to Gaussian and Matern kernels, we prove that multi-layer kernel machines can achieve $O(n^2\log^2n)$ computational time and $O(n\log^2n)$ storage space, and yield fast and minimax optimal approximations to the KRR estimate for nonparametric regression. Moreover, we construct uncertainty quantification for multi-layer kernel machines by using conformal prediction techniques with robust coverage properties. The analysis and theoretical predictions are supported by simulations and real data examples.

stat.ME↗