Elynn Chen
YOU?
Author Swipe
View article: ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation
ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation Open
Missing data in financial panels presents a critical obstacle, undermining asset-pricing models and reducing the effectiveness of investment strategies. Such panels are often inherently multi-dimensional, spanning firms, time, and financia…
View article: Time-Varying Factor-Augmented Models for Volatility Forecasting
Time-Varying Factor-Augmented Models for Volatility Forecasting Open
Accurate volatility forecasts are vital in modern finance for risk management, portfolio allocation, and strategic decision-making. However, existing methods face key limitations. Fully multivariate models, while comprehensive, are computa…
View article: Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs
Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs Open
We study meta-reinforcement learning in finite-horizon MDPs where related tasks share similar structures in their optimal action-value functions. Specifically, we posit a linear representation $Q^*_h(s,a)=Φ_h(s,a)\,θ^{(k)}_h$ and place a G…
View article: Exploring Causal Effects of Hormone‐ and Radio‐Treatments in an Observational Study of Breast Cancer Using Copula‐Based Semi‐Competing Risks Models
Exploring Causal Effects of Hormone‐ and Radio‐Treatments in an Observational Study of Breast Cancer Using Copula‐Based Semi‐Competing Risks Models Open
Breast cancer patients may experience relapse or death after surgery during the follow‐up period, leading to dependent censoring of relapse. This phenomenon, known as semi‐competing risk, imposes challenges in analyzing treatment effects o…
View article: High-Dimensional Linear Bandits under Stochastic Latent Heterogeneity
High-Dimensional Linear Bandits under Stochastic Latent Heterogeneity Open
This paper addresses the critical challenge of stochastic latent heterogeneity in online decision-making, where individuals' responses to actions vary not only with observable contexts but also with unobserved, randomly realized subgroups.…
View article: Transition Transfer $Q$-Learning for Composite Markov Decision Processes
Transition Transfer $Q$-Learning for Composite Markov Decision Processes Open
To bridge the gap between empirical success and theoretical understanding in transfer reinforcement learning (RL), we study a principled approach with provable performance guarantees. We introduce a novel composite MDP framework where high…
View article: Statistical Inference for Low-Rank Tensor Models
Statistical Inference for Low-Rank Tensor Models Open
Statistical inference for tensors has emerged as a critical challenge in analyzing high-dimensional data in modern data science. This paper introduces a unified framework for inferring general and low-Tucker-rank linear functionals of low-…
View article: TEAFormers: TEnsor-Augmented Transformers for Multi-Dimensional Time Series Forecasting
TEAFormers: TEnsor-Augmented Transformers for Multi-Dimensional Time Series Forecasting Open
Multi-dimensional time series data, such as matrix and tensor-variate time series, are increasingly prevalent in fields such as economics, finance, and climate science. Traditional Transformer models, though adept with sequential data, do …
View article: Conditional Uncertainty Quantification for Tensorized Topological Neural Networks
Conditional Uncertainty Quantification for Tensorized Topological Neural Networks Open
Graph Neural Networks (GNNs) have become the de facto standard for analyzing graph-structured data, leveraging message-passing techniques to capture both structural and node feature information. However, recent studies have raised concerns…
View article: Tensor-Fused Multi-View Graph Contrastive Learning
Tensor-Fused Multi-View Graph Contrastive Learning Open
Graph contrastive learning (GCL) has emerged as a promising approach to enhance graph neural networks' (GNNs) ability to learn rich representations from unlabeled graph-structured data. However, current GCL models face challenges with comp…
View article: High-Dimensional Tensor Discriminant Analysis with Incomplete Tensors
High-Dimensional Tensor Discriminant Analysis with Incomplete Tensors Open
Tensor classification is gaining importance across fields, yet handling partially observed data remains challenging. In this paper, we introduce a novel approach to tensor classification with incomplete data, framed within high-dimensional…
View article: High-Dimensional Tensor Classification with CP Low-Rank Discriminant Structure
High-Dimensional Tensor Classification with CP Low-Rank Discriminant Structure Open
Tensor classification has become increasingly crucial in statistics and machine learning, with applications spanning neuroimaging, computer vision, and recommendation systems. However, the high dimensionality of tensors presents significan…
View article: Exploring causal effects of hormone- and radio-treatments in an observational study of breast cancer using copula-based semi-competing risks models
Exploring causal effects of hormone- and radio-treatments in an observational study of breast cancer using copula-based semi-competing risks models Open
Breast cancer patients may experience relapse or death after surgery during the follow-up period, leading to dependent censoring of relapse. This phenomenon, known as semi-competing risk, imposes challenges in analyzing treatment effects o…
View article: Factor Augmented Matrix Regression
Factor Augmented Matrix Regression Open
We introduce \underline{F}actor-\underline{A}ugmented \underline{Ma}trix \underline{R}egression (FAMAR) to address the growing applications of matrix-variate data and their associated challenges, particularly with high-dimensionality and c…
View article: Dynamic Contextual Pricing with Doubly Non-Parametric Random Utility Models
Dynamic Contextual Pricing with Doubly Non-Parametric Random Utility Models Open
In the evolving landscape of digital commerce, adaptive dynamic pricing strategies are essential for gaining a competitive edge. This paper introduces novel {\em doubly nonparametric random utility models} that eschew traditional parametri…
View article: Time-Varying Matrix Factor Models
Time-Varying Matrix Factor Models Open
Matrix-variate data of high dimensions are frequently observed in finance and economics, spanning extended time periods, such as the long-term data on international trade flows among numerous countries. To address potential structural shif…
View article: Semi-parametric tensor factor analysis by iteratively projected singular value decomposition
Semi-parametric tensor factor analysis by iteratively projected singular value decomposition Open
This paper introduces a general framework of Semi-parametric TEnsor Factor Analysis (STEFA) that focuses on the methodology and theory of low-rank tensor decomposition with auxiliary covariates. Semi-parametric TEnsor Factor Analysis model…
View article: Reinforcement Learning in Latent Heterogeneous Environments
Reinforcement Learning in Latent Heterogeneous Environments Open
Reinforcement Learning holds great promise for data-driven decision-making in various social contexts, including healthcare, education, and business. However, classical methods that focus on the mean of the total return may yield misleadin…
View article: MEV Makes Everyone Happy under Greedy Sequencing Rule
MEV Makes Everyone Happy under Greedy Sequencing Rule Open
Trading through decentralized exchanges (DEXs) has become crucial in today's blockchain ecosystem, enabling users to swap tokens efficiently and automatically. However, the capacity of miners to strategically order transactions has led to …
View article: Modeling Dynamic Transport Network with Matrix Factor Models: an Application to International Trade Flow
Modeling Dynamic Transport Network with Matrix Factor Models: an Application to International Trade Flow Open
International trade research plays an important role to inform trade policy and shed light on wider economic issues. With recent advances in information technology, economic agencies distribute an enormous amount of internationally compara…
View article: Reinforcement Learning with Heterogeneous Data: Estimation and Inference
Reinforcement Learning with Heterogeneous Data: Estimation and Inference Open
Reinforcement Learning (RL) has the promise of providing data-driven support for decision-making in a wide range of problems in healthcare, education, business, and other domains. Classical RL methods focus on the mean of the total return …
View article: Statistical Inference for High-Dimensional Matrix-Variate Factor Models
Statistical Inference for High-Dimensional Matrix-Variate Factor Models Open
This article considers the estimation and inference of the low-rank components in high-dimensional matrix-variate factor models, where each dimension of the matrix-variates (p × q) is comparable to or greater than the number of observation…
View article: On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification
On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification Open
Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the behavior of minimum Wasserstein estimators is poorly understo…
View article: Statistical Inference for High-Dimensional Matrix-Variate Factor Model
Statistical Inference for High-Dimensional Matrix-Variate Factor Model Open
This paper considers the estimation and inference of the low-rank components in high-dimensional matrix-variate factor models, where each dimension of the matrix-variates ($p \times q$) is comparable to or greater than the number of observ…
View article: Helping Effects Against Curse of Dimensionality in Threshold Factor Models for Matrix Time Series
Helping Effects Against Curse of Dimensionality in Threshold Factor Models for Matrix Time Series Open
As is known, factor analysis is a popular method to reduce dimension for high-dimensional data. For matrix data, the dimension reduction can be more effectively achieved through both row and column directions. In this paper, we introduce a…