About

Yuting Wu Chen is an Associate Professor in the Department of Electrical and Computer Engineering at the University of Illinois Urbana-Champaign. He holds a Ph.D. and M.S. in Electrical Engineering from Rensselaer Polytechnic Institute, earned in 2011 and 2009 respectively, and a B.S. in Electrical Engineering from the University of Illinois at Urbana-Champaign obtained in 2007. His research focuses on the development of anti-reflection implementations for terahertz waves, broadband antireflection photonic devices with graded refractive indices, and the engineering of three-dimensional inverted photonic gratings for broadband antireflection of terahertz waves. His work has contributed to advancements in optical and photonic technologies, with features highlighted in research publications such as Nature Photonics. In addition to his research, he is involved in teaching and leadership development, offering courses in electrical and computer engineering, and engaging in initiatives that promote engineering education and outreach.

Research topics

• Computer Science
• Statistics
• Mathematics
• Artificial Intelligence
• Data Mining
• Operations research
• Combinatorics
• Data science
• Algorithm
• Virology
• Econometrics
• Psychology
• Medicine
• Engineering

Selected publications

• Semiparametric analysis for paired comparisons with covariates

  arXiv (Cornell University) · 2026-03-31

  articleOpen accessSenior author

  Statistical inference in parametric models (e.g., the Bradley--Terry model and its variants) for paired-comparison data has been explored in the high-dimensional regime, in which the number of items involving in paired comparisons diverges. However, parametric models are highly susceptible to model misspecification. To relax the assumption of known distributions and provide flexibility, we propose a semiparametric framework for modeling the merits of items and covariate effects (e.g., home-field advantage) by introducing latent random variables with unspecified distributions. As the number of parameters increases with the number of items, semiparametric inference is highly nontrivial. To address this issue, we employ a kernel-based least squares approach to estimate all unknown parameters. When each pair of items has a fixed number of comparisons and the number of items tends to infinity, we prove the consistency of all resulting estimators and derive their asymptotic normal distributions. To the best of our knowledge, this is the first study to conduct a semiparametric analysis of paired comparisons with an increasing dimension. We conduct simulations to evaluate the finite-sample performance of the proposed method and illustrate its practical utility by analyzing an NBA dataset.

  PublisherOA PDF

• Semiparametric analysis for paired comparisons with covariates

  arXiv (Cornell University) · 2026-03-31

  preprintOpen accessSenior author

  Statistical inference in parametric models (e.g., the Bradley--Terry model and its variants) for paired-comparison data has been explored in the high-dimensional regime, in which the number of items involving in paired comparisons diverges. However, parametric models are highly susceptible to model misspecification. To relax the assumption of known distributions and provide flexibility, we propose a semiparametric framework for modeling the merits of items and covariate effects (e.g., home-field advantage) by introducing latent random variables with unspecified distributions. As the number of parameters increases with the number of items, semiparametric inference is highly nontrivial. To address this issue, we employ a kernel-based least squares approach to estimate all unknown parameters. When each pair of items has a fixed number of comparisons and the number of items tends to infinity, we prove the consistency of all resulting estimators and derive their asymptotic normal distributions. To the best of our knowledge, this is the first study to conduct a semiparametric analysis of paired comparisons with an increasing dimension. We conduct simulations to evaluate the finite-sample performance of the proposed method and illustrate its practical utility by analyzing an NBA dataset.

  PublisherDOI

• Inference in Semiparametric Formation Models for Directed Networks

  Journal of Business and Economic Statistics · 2025-06-06

  articleSenior author
  PublisherDOI

• Network Cross-Validation and Model Selection via Subsampling

  ArXiv.org · 2025-04-09

  preprintOpen accessSenior author

  Complex and larger networks are becoming increasingly prevalent in scientific applications in various domains. Although a number of models and methods exist for such networks, cross-validation on networks remains challenging due to the unique structure of network data. In this paper, we propose a general cross-validation procedure called NETCROP (NETwork CRoss-Validation using Overlapping Partitions). The key idea is to divide the original network into multiple subnetworks with a shared overlap part, producing training sets consisting of the subnetworks and a test set with the node pairs between the subnetworks. This train-test split provides the basis for a network cross-validation procedure that can be applied on a wide range of model selection and parameter tuning problems for networks. The method is computationally efficient for large networks as it uses smaller subnetworks for the training step. We provide methodological details and theoretical guarantees for several model selection and parameter tuning tasks using NETCROP. Numerical results demonstrate that NETCROP performs accurate cross-validation on a diverse set of network model selection and parameter tuning problems. The results also indicate that NETCROP is computationally much faster while being often more accurate than the existing methods for network cross-validation.

  PublisherOA PDFDOI

• A spike-and-slab prior for dimension selection in generalized linear network eigenmodels

  Biometrika · 2025-01-01 · 1 citations

  articleSenior author

  Summary Latent space models are often used to model network data by embedding a network’s nodes into a low-dimensional latent space; however, choosing the dimension of this space remains a challenge. To this end, we begin by formalizing a class of latent space models we call generalized linear network eigenmodels that can model various edge types (binary, ordinal, nonnegative continuous) found in scientific applications. This model class subsumes the traditional eigenmodel by embedding it in a generalized linear model with an exponential dispersion family random component and fixes identifiability issues that hindered interpretability. We propose a Bayesian approach to dimension selection for generalized linear network eigenmodels based on an ordered spike-and-slab prior that provides improved dimension estimation and satisfies several appealing theoretical properties. We show that the model’s posterior is consistent and concentrates on low-dimensional models near the truth. We demonstrate our approach’s consistent dimension selection on simulated networks, and we use generalized linear network eigenmodels to study the effect of covariates on the formation of networks from biology, ecology and economics and the existence of residual latent structure.

  PublisherDOI

• Inference in semiparametric formation models for directed networks

  arXiv (Cornell University) · 2024-05-30

  preprintOpen accessSenior author

  We propose a semiparametric model for dyadic link formations in directed networks. The model contains a set of degree parameters that measure different effects of popularity or outgoingness across nodes, a regression parameter vector that reflects the homophily effect resulting from the nodal attributes or pairwise covariates associated with edges, and a set of latent random noises with unknown distributions. Our interest lies in inferring the unknown degree parameters and homophily parameters. The dimension of the degree parameters increases with the number of nodes. Under the high-dimensional regime, we develop a kernel-based least squares approach to estimate the unknown parameters. The major advantage of our estimator is that it does not encounter the incidental parameter problem for the homophily parameters. We prove consistency of all the resulting estimators of the degree parameters and homophily parameters. We establish high-dimensional central limit theorems for the proposed estimators and provide several applications of our general theory, including testing the existence of degree heterogeneity, testing sparse signals and recovering the support. Simulation studies and a real data application are conducted to illustrate the finite sample performance of the proposed methods.

  PublisherOA PDFDOI

• Orthogonal Symmetric Non-Negative Matrix Factorization Under the Stochastic Block Model

  Statistica Sinica · 2024-11-11

  articleSenior author
  PublisherDOI

• Contribution of Tinnitus and Hearing Loss to Depression: NHANES Population Study

  Ear and Hearing · 2024-01-31 · 17 citations

  article

  OBJECTIVES: Hearing loss affects the emotional well-being of adults and is sometimes associated with clinical depression. Chronic tinnitus is highly comorbid with hearing loss and separately linked with depression. In this article, the authors investigated the combined effects of hearing loss and tinnitus on depression in the presence of other moderating influences such as demographic, lifestyle, and health factors. DESIGN: The authors used the National Health and Nutrition Examination Survey data (2011-2012 and 2015-2016) to determine the effects of hearing loss and tinnitus on depression in a population of US adults (20 to 69 years). The dataset included the Patient Health Questionnaire-9 for depression screening, hearing testing using pure-tone audiometry, and information related to multiple demographic, lifestyle, and health factors (n = 5845). RESULTS: The statistical analysis showed moderate to high associations between depression and hearing loss, tinnitus, and demographic, lifestyle, and health factors, separately. Results of logistic regression analysis revealed that depression was significantly influenced by hearing loss (adjusted odds ratios [OR] = 3.0), the functional impact of tinnitus (adjusted OR = 2.4), and their interaction, both in the absence or presence of the moderating influences. The effect of bothersome tinnitus on depression was amplified in the presence of hearing loss (adjusted OR = 2.4 in the absence of hearing loss to adjusted OR = 14.9 in the presence of hearing loss). Conversely, the effect of hearing loss on depression decreased when bothersome tinnitus was present (adjusted OR = 3.0 when no tinnitus problem was present to adjusted OR = 0.7 in the presence of bothersome tinnitus). CONCLUSIONS: Together, hearing loss and bothersome tinnitus had a significant effect on self-reported depression symptoms, but their relative effect when comorbid differed. Tinnitus remained more salient than hearing loss and the latter's contribution to depression was reduced in the presence of tinnitus, but the presence of hearing loss significantly increased the effects of tinnitus on depression, even when the effects of the relevant demographic, lifestyle, or health factors were controlled. Treatment strategies that target depression should screen for hearing loss and bothersome tinnitus and provide management options for the conditions.

  PublisherDOI

• Scalable Estimation and Two-Sample Testing for Large Networks via Subsampling

  Journal of Computational and Graphical Statistics · 2024-11-25 · 4 citations

  articleSenior authorCorresponding
  PublisherDOI

• Current-Based Design of Ferroelectric Approximate Search Memory

  Journal of Computer-Aided Design & Computer Graphics · 2023-05-01

  articleOpen access1st authorCorresponding

  <p indent="0mm">In the models with excellent fault-tolerance to hardware, approximate search can deal with the higher efficiency requirement of the amount of data and processing. A current based measurement scheme is proposed in this paper for the existing ternary content addressable memories in approximate search mode array suffered poor accuracy and scalability. The memory architecture is improved by ferroelectric field effect transistor aiming to achieve low power and area; the architecture of the proposed memory cell replaces the voltage-based output signal with the current-based one, which efficiently increases the scalability of the array; a sense amplifier which converts the analog signal to digital spike signal is introduced as the peripheral circuitry to measure the output of the mismatch numbers of the TCAM array. Through the transient simulation circuit in Hspice and Virtuoso software simulation platform, the results indicate that the high energy efficiency approximate search is successfully achieved.

  PublisherOA PDFDOI

Recent grants

• CMG--Particle Filtering for Time-Dependent Tomographic Analysis of the Solar Atmosphere

  NSF · $838k · 2006–2012

• Variational Inference for Complex Networks

  NSF · $150k · 2020–2024

• Monte Carlo Methods for Complex Problems: From Data Augmentation to Likelihood Free Inference

  NSF · $260k · 2008–2011

• Sequential Monte Carlo Methods for Computationally Intensive Problems

  NSF · $85k · 2005–2008

• Sampling for Statistical Inference on Network Data

  NSF · $180k · 2011–2015

Frequent coauthors

• Subhadeep Paul

  12 shared

• Ian H. Dinwoodie

  10 shared

• Daniel K. Sewell

  9 shared

• Tianmao Lai

  8 shared

• Chengjun Li

  Guangzhou University

  8 shared

• Jingfei Zhang

  6 shared

• Joshua Daniel Loyal

  6 shared

• Ying Jiang

  6 shared

Awards & honors

• Alumni Award for Distinguished Service