WTWenpin Tang

Wenpin Tang

*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


Wenpin Tang has a total of 51 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Finite and Infinite Weighted Exchangeable Sequences

    by Wenpin Tang

    Motivated by recent interest in predictive inference under distribution shifts, we study the problem of approximating finite weighted exchangeable sequences by a mixture of finite sequences with independent terms. Two different approaches are developed: a combinatorial approach and a probabilistic approach. Various bounds are derived in terms of weight functions, extending previous results on finite exchangeable sequences. As a byproduct, we obtain a version of de Finetti’s theorem for infinite weighted exchangeable sequences, recovering an instance of Barber, Candes, Ramdas and Tibshirani 1 (Bernoulli, 30 (2024), pp. 3004–3028) in the Polish space with bounded and continuous weights.

  • Contractive Diffusion Probabilistic Models

    by Wenpin Tang, Hanyang Zhao

    Diffusion probabilistic models (DPMs) have emerged as a promising technique in generative modeling. The success of DPMs relies on two ingredients: time reversal of diffusion processes and score matching. In view of possibly unguaranteed score matching, we propose a new criterion—the contraction property of backward sampling in the design of DPMs, leading to a novel class of contractive DPMs (CDPMs). Our key insight is that the contraction property can provably narrow score-matching errors and discretization errors; thus our proposed CDPMs are robust to both sources of error. For practical use, we showcase that CDPM can leverage weights of pretrained DPMs by a simple transformation, without the necessity of further training. We corroborated our approach by experiments on Swiss Roll, MNIST, CIFAR-10 32[Formula: see text]32, and AFHQ 64[Formula: see text]64 dataset. Notably, CDPM steadily improves the performance of baseline score-based diffusion models.


  • Open Access

    Bayesian Geostatistics Using Predictive Stacking

    by Lu Zhang, Wenpin Tang, Sudipto Banerjee

    We develop Bayesian predictive stacking for geostatistical models, where the primary inferential objective is to provide inference on the latent spatial random field and conduct spatial predictions at arbitrary locations. We exploit analytically tractable posterior distributions for regression coefficients of predictors and the realizations of the spatial process conditional upon process parameters. We subsequently combine such inference by stacking these models across the range of values of the hyper-parameters. We devise stacking of means and posterior densities in a manner that is computationally efficient without resorting to iterative algorithms such as Markov chain Monte Carlo (MCMC) and can exploit the benefits of parallel computations. We offer novel theoretical insights into the resulting inference within an infill asymptotic paradigm and through empirical results showing that stacked inference is comparable to full sampling-based Bayesian inference at a significantly lower computational cost.


  • The Convergence Rate of Vanishing Viscosity Approximations for Mean Field Games

    by Wenpin Tang, Yuming Paul Zhang

    Motivated by numerical challenges in first-order mean field games (MFGs) and the weak noise theory for the Kardar–Parisi–Zhang equation, we consider the problem of vanishing viscosity approximations for MFGs. We provide the first results on the convergence rate to the vanishing viscosity limit in mean field games, with a focus on the dimension dependence of the rate exponent. Two cases are studied: MFGs with a local coupling and those with a nonlocal, regularizing coupling. In the former case, we use a duality approach and our results suggest that there may be a phase transition in the dimension dependence of vanishing viscosity approximations in terms of the growth of the Hamiltonian and the local coupling. In the latter case, we rely on the regularity analysis of the solution, and derive a faster rate compared to MFGs with a local coupling. A list of open problems are presented.


  • Top Cited Papers
    Open Access

    Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey

    by Genta Indra Winata, Hanyang Zhao, Anirban Das, Wenpin Tang, David D. Yao, Shi-Xiong Zhang, Sambit Sahu

    Preference tuning is a crucial process for aligning deep generative models with human preferences. This survey offers a thorough overview of recent advancements in preference tuning and the integration of human feedback. The paper is organized into three main sections: 1) introduction and preliminaries: an introduction to reinforcement learning frameworks, preference tuning tasks, models, and datasets across various modalities: language, speech, and vision, as well as different policy approaches, 2) in-depth exploration of each preference tuning approach: a detailed analysis of the methods used in preference tuning, and 3) applications, discussion, and future directions: an exploration of the applications of preference tuning in downstream tasks, including evaluation methods for different modalities, and an outlook on future research directions. Our objective is to present the latest methodologies in preference tuning and model alignment, enhancing the understanding of this field for researchers and practitioners. We hope to encourage further engagement and innovation in this area. Additionally, we provide a GitHub link https://github.com/hanyang1999/Preference-Tuning-with-Human-Feedback.


  • Open Access

    Systemic Robustness: A Mean‐Field Particle System Approach

    by Erhan Bayraktar, Gaoyue Guo, Wenpin Tang, Yuming Paul Zhang

    This paper is concerned with the problem of capital provision in a large particle system modeled by stochastic differential equations involving hitting times, which arises from considerations of systemic risk in a financial network. Motivated by Tang and Tsai, we focus on the number or proportion of surviving entities that never default to measure the systemic robustness. First we show that the mean‐field particle system and its limit McKean–Vlasov equation are both well‐posed by virtue of the notion of minimal solutions. We then establish a connection between the proportion of surviving entities in the large particle system and the probability of default in the McKean–Vlasov equation as the size of the interacting particle system tends to infinity. Finally, we study the asymptotic efficiency of capital provision for different drift , which is linked to the economy regime: The expected number of surviving entities has a uniform upper bound if ; it is of order if ; and it is of order if , where the effect of capital provision is negligible.


  • Polynomial Voting Rules

    by Wenpin Tang, David D. Yao

    We propose and study a new class of polynomial voting rules for a general decentralized decision/consensus system, and more specifically for the proof-of-stake protocol. The main idea, inspired by the Penrose square-root law and the more recent quadratic voting rule, is to differentiate a voter’s voting power and the voter’s share (fraction of the total in the system). We show that, whereas voter shares form a martingale process that converges to a Dirichlet distribution, their voting powers follow a supermartingale process that decays to zero over time. This prevents any voter from controlling the voting process and, thus, enhances security. For both limiting results, we also provide explicit rates of convergence. When the initial total volume of votes (or stakes) is large, we show a phase transition in share stability (or the lack thereof), corresponding to the voter’s initial share relative to the total. We also study the scenario in which trading (of votes/stakes) among the voters is allowed and quantify the level of risk sensitivity (or risk aversion) in three categories, corresponding to the voter’s utility being a supermartingale, a submartingale, and a martingale. For each category, we identify the voter’s best strategy in terms of participation and trading. Funding: W. Tang gratefully acknowledges financial support through the National Science Foundation [Grants DMS-2113779 and DMS-2206038] and through a start-up grant at Columbia University. D. D. Yao’s work is part of a Columbia–City University/Hong Kong collaborative project that is supported by InnoHK Initiative, the Government of Hong Kong Special Administrative Region, and the Laboratory for AI-Powered Financial Technologies.


  • Top Cited Papers

    Policy Iteration for the Deterministic Control Problems—A Viscosity Approach

    by Wenpin Tang, Hung Vinh Tran, Yuming Paul Zhang

    This paper is concerned with the convergence rate of policy iteration for (deterministic) optimal control problems in continuous time. To overcome the problem of ill-posedness due to lack of regularity, we consider a semidiscrete scheme by adding a viscosity term via finite differences in space. We prove that the policy iteration (PI) for the semidiscrete scheme converges exponentially fast and provide a bound on the error induced by the semidiscrete scheme. We also consider the discrete space-time scheme, where both space and time are discretized. The convergence rate of PI and the discretization error are studied.


  • Open Access

    Score-based diffusion models via stochastic differential equations

    by Wenpin Tang, Hanyang Zhao

    This is an expository article on the score-based diffusion models, with a particular focus on the formulation via stochastic differential equations (SDE). After a gentle introduction, we discuss the two pillars in the diffusion modeling – sampling and score matching, which encompass the SDE/ODE sampling, score matching efficiency, the consistency models, and reinforcement learning. Short proofs are given to illustrate the main idea of the stated results. The article is primarily a technical introduction to the field, and practitioners may also find some analysis useful in designing new models or algorithms.