KWKaizheng Wang

Kaizheng Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Kaizheng Wang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Learning a Size-Weight Frontier for Synthetic-Augmented Inference

    by Chengpiao Huang, Kaizheng Wang

    Synthetic data can improve statistical inference when real data are scarce, but naively treating synthetic samples as real data can introduce bias and lead to unreliable inference. We develop a general framework for synthetic-augmented inference across a population of related tasks. It characterizes synthetic augmentation by the number of synthetic observations and their weight. Central to our framework is a size-weight frontier that specifies, for each weight, the largest synthetic sample size for which all smaller sizes attain the target task-marginal coverage. We estimate this frontier from historical tasks, and establish a finite-sample coverage guarantee simultaneously for all size-weight configurations on or below the estimated frontier. In experiments using large language model responses to augment opinion survey data, our procedure achieves target coverage and substantially narrows confidence intervals.

  • Transfer Learning of CATE with Kernel Ridge Regression

    by Seok-Jin Kim, Hongjie Liu, Molei Liu, Kaizheng Wang

    1 IntroductionPredicting the conditional average treatment effect (CATE) given the covariates of an individual enables more precise and personalized decision-making in various application fields (K...

  • Open Access

    LLM-Powered Virtual Population for Demand Simulation and Pricing

    by Chengpiao Huang, Kaizheng Wang

    We develop an LLM-powered virtual population model that simulates demand for pricing decisions, in settings where products are described by rich unstructured information, such as text descriptions and images, and where decision makers need not only mean-demand predictions but also uncertainty estimates for counterfactual prices. Our model represents exposed customers as draws from a finite mixture of customer personas. For each persona, product, and candidate price, an LLM elicits a persona-level purchase probability using both structured persona information and unstructured product information. These probabilities are aggregated through calibrated mixture weights to form a predictive distribution of aggregate demand. The resulting simulator can evaluate counterfactual prices under various pricing objectives, including expected revenue and risk-aware criteria such as conditional value at risk. We test the framework on an online H&M fashion dataset with product descriptions and images. The calibrated LLM-based simulator achieves the best overall predictive performance among the models considered, and supports sample-efficient pricing decisions. Our framework provides a practical way to use LLMs as demand simulators for products with limited historical demand data but rich product information. By producing a full predictive demand distribution rather than only a point forecast, it enables managers to compare candidate prices, quantify demand uncertainty, and choose prices that target either average-case revenue or risk-aware objectives.

  • Open Access

    Adaptive Querying with AI Persona Priors

    by Kaizheng Wang, Yuhang Wu, Assaf Zeevi

    We study adaptive querying for learning user-dependent quantities of interest, such as responses to held-out items and psychometric indicators, within tight query budgets. Classical Bayesian design and computerized adaptive testing typically rely on restrictive parametric assumptions or expensive posterior approximations, limiting their use in heterogeneous, high-dimensional, and cold-start settings. We introduce a persona-induced latent variable model that represents a user's state through membership in a finite dictionary of AI personas, each offering response distributions produced by a large language model. This yields expressive priors with closed-form posterior updates and efficient finite-mixture predictions, enabling scalable Bayesian design for sequential item selection. Experiments on synthetic data and WorldValuesBench demonstrate that persona-based posteriors deliver accurate probabilistic predictions and an interpretable adaptive elicitation pipeline.

  • A Particle Algorithm for Mean-Field Variational Inference

    by Qiang Du, Kaizheng Wang, Edith Zhang, Chenyang Zhong

    Variational inference (VI) is a fast and scalable alternative to Markov chain Monte Carlo and has been widely applied to posterior inference tasks in statistics and machine learning. A traditional approach for implementing mean-field variational inference (MFVI) is coordinate ascent variational inference (CAVI), which relies crucially on parametric assumptions on complete conditionals. We introduce a novel particle-based algorithm for MFVI, named PArticle VI (PAVI), for nonparametric mean-field approximation. We obtain nonasymptotic error bounds for our algorithm. To the best of our knowledge, this is the first end-to-end guarantee for particle-based MFVI.


  • Open Access

    SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation

    by Grace Jiarui Fan, Chengpiao Huang, Tianyi Peng, Kaizheng Wang, Yuhang Wu

    AI-based persona simulation---often referred to as digital twin simulation---is increasingly used for market research, recommender systems, and social sciences. Despite their flexibility, large language models (LLMs) often exhibit systematic bias and miscalibration relative to real human behavior, limiting their reliability. Inspired by synthetic control methods from causal inference, we propose SYN-DIGITS (SYNthetic Control Framework for Calibrated DIGItal Twin Simulation), a principled and lightweight calibration framework that learns latent structure from digital-twin responses and transfers it to align predictions with human ground truth. SYN-DIGITS operates as a post-processing layer on top of any LLM-based simulator and thus is model-agnostic. We develop a latent factor model that formalizes when and why calibration succeeds through latent space alignment conditions, and we systematically evaluate ten calibration methods across thirteen persona constructions, three LLMs, and two datasets. SYN-DIGITS supports both individual-level and distributional simulation for previously unseen questions and unobserved populations, with provable error guarantees. Experiments show that SYN-DIGITS achieves up to 50% relative improvements in individual-level correlation and 50-90% relative reductions in distributional discrepancy compared to uncalibrated baselines.

  • Open Access

    Model-Free Assessment of Simulator Fidelity via Quantile Curves

    by Yu-Shiou Lin, Kaizheng Wang, Garud Iyengar

    As generative AI models are increasingly used to simulate real-world systems, quantifying the "sim-to-real" gap is critical. The distributional discrepancy between real and simulated outputs is a random variable driven by the stochastic input scenario. A fundamental challenge is that for any given input, the ground-truth and simulated output distributions are only observable through finite batches of samples, often of heterogeneous sizes. This renders standard predictive inference methods inapplicable, as they seek to quantify uncertainty in observable outputs rather than their underlying population parameters. To address this, we construct confidence sets for these latent parameters and use them to derive a robust proxy for the sim-to-real discrepancy. We then estimate the quantile function of this proxy to provide a comprehensive risk profile of the simulator. Our method is model-agnostic and handles general output spaces, such as categorical survey responses and continuous multi-dimensional sensor data. By rigorously accounting for sampling error, the resulting risk profile supports statistical inference for the real output distribution in a new scenario, the calculation of risk measures like Conditional Value-at-Risk (CVaR), and principled comparisons across simulators. We demonstrate the practical utility of this method by evaluating the alignment of four major LLMs with human populations on the WorldValueBench dataset.

  • Top Cited Papers

    Pseudo-Labeling for kernel ridge regression under covariate shift

    by Kaizheng Wang

    We develop and analyze a principled approach to kernel ridge regression under covariate shift. The goal is to learn a regression function with small mean squared error over a target distribution, based on unlabeled data from there and labeled data that may have a different feature distribution. We propose to split the labeled data into two subsets, and conduct kernel ridge regression on them separately to obtain a collection of candidate models and an imputation model. We use the latter to fill the missing labels and then select the best candidate accordingly. Our nonasymptotic excess risk bounds demonstrate that our estimator adapts effectively to both the structure of the target distribution and the covariate shift. This adaptation is quantified through a notion of effective sample size that reflects the value of labeled source data for the target regression task. Our estimator achieves the minimax optimal error rate up to a polylogarithmic factor, and we find that using pseudo-labels for model selection does not significantly hinder performance.


  • A Stability Principle for Learning Under Nonstationarity

    by Chengpiao Huang, Kaizheng Wang

    Adapting to a Changing Environment with Steady Decisions Most real-world decision making unfolds in changing environments. When yesterday’s data may no longer depict today, how much past data should guide future decision making? Use too little and you chase noise; use too much and you overlook new trends. In “A Stability Principle for Learning under Nonstationarity,” Huang and Wang propose a simple stability principle: keep adding past data until the bias it incurs exceeds the natural statistical noise. Their theory shows that the proposed approach can optimally adapt to unforeseeable changes in the environment for a broad spectrum of statistical learning and decision-making problems. At its core are a novel similarity measure for different decision-making objectives and a segmentation technique that breaks down the nonstationary data stream into quasistationary pieces. Simulations and real-data experiments spanning several nonstationarity patterns confirm the approach’s ability to make steady yet responsive decisions.