[YOUR NAME]

Bio

I am a first-year PhD student at Carnegie Mellon University. My research focuses on developing principled frameworks for machine learning and statistical inference in complex systems, with applications to scientific discovery. My current interests include:

AI for Science

How can we integrate modern AI into scientific workflows to accelerate discovery from complex, high-dimensional data, while ensuring conclusions remain reliable and interpretable?

Causal Inference

How can we leverage machine learning to estimate causal effects with statistical validity, and design robust methods under confounding, selection bias, and distribution shift?

Statistical Machine Learning

What are the limits of learning, and how can we design reliable, provably optimal algorithms for high-dimensional data under modern challenges like dependence and heterogeneity?

News

Dec 2025 Our paper on feature importance ranking is accepted to TMLR!

Publications

ALL / BY AREA / BY TYPE

Selected
Preprint
Conference
Journal

Deep Memory Unrolled Networks for Solving Imaging Linear Inverse Problems Abstract PDF Slides

Yuxi Chen, Xi Chen, Shirin Jalali, Arian Maleki

Sampling Theory and Applications (SampTA), 2025 (Oral)

Unrolled networks have emerged as one of the most successful methods in imaging applications. Although they have demonstrated remarkable efficacy in solving specific computer vision and computational imaging tasks, their adaptation to other applications presents considerable challenges. This is primarily due to the multitude of design decisions that practitioners working on new applications must navigate, each potentially affecting the network's overall performance. These decisions include selecting the optimization algorithm to unroll, defining the loss function, deciding on the structure of residual connections, and determining the number of convolutional layers, among others. Compounding the issue, evaluating each design choice requires time-consuming simulations to train the neural network. As a result, the process of exploring multiple options and identifying the optimal configuration becomes time-consuming and computationally demanding. The main objectives of this paper are (1) to unify some ideas and methodologies used in unrolled networks to reduce the number of design choices a user has to make, and (2) to report a comprehensive numerical study to discover the optimal design choices. We anticipate that this study will help scientists and engineers design unrolled networks for their applications and diagnose problems within their networks efficiently.

Top-k Feature Importance Ranking Abstract PDF

Yuxi Chen, Tiffany Tang, Genevera Allen

Transactions on Machine Learning Research (TMLR), 2025

Accurate ranking of important features is a fundamental challenge in interpretable machine learning with critical applications in scientific discovery and decision-making. Unlike feature selection and feature importance, the specific problem of ranking important features has received considerably less attention. We introduce RAMPART (Ranked Attributions with MiniPatches And Recursive Trimming), a framework that utilizes any existing feature importance measure in a novel algorithm specifically tailored for ranking the top-k features. Our approach combines an adaptive sequential halving strategy that progressively focuses computational resources on promising features with an efficient ensembling technique using both observation and feature subsampling. Unlike existing methods that convert importance scores to ranks as post-processing, our framework explicitly optimizes for ranking accuracy. We provide theoretical guarantees showing that RAMPART achieves the correct top-k ranking with high probability under mild conditions, and demonstrate through extensive simulation studies that RAMPART consistently outperforms popular feature importance methods, concluding with two high-dimensional genomics case studies.

Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problems Abstract PDF

Yuxi Chen, Xi Chen, Arian Maleki, Shirin Jalali

Entropy (Special Issue on Advances in Computational Imaging), 2025

Unrolled networks have become prevalent in various computer vision and imaging tasks. Although they have demonstrated remarkable efficacy in solving specific computer vision and computational imaging tasks, their adaptation to other applications presents considerable challenges. This is primarily due to the multitude of design decisions that practitioners working on new applications must navigate, each potentially affecting the network's overall performance. These decisions include selecting the optimization algorithm, defining the loss function, and determining the deep architecture, among others. Compounding the issue, evaluating each design choice requires time-consuming simulations to train, fine-tune the neural network, and optimize its performance. As a result, the process of exploring multiple options and identifying the optimal configuration becomes time-consuming and computationally demanding. The main objectives of this paper are (1) to unify some ideas and methodologies used in unrolled networks to reduce the number of design choices a user has to make, and (2) to report a comprehensive ablation study to discuss the impact of each of the choices involved in designing unrolled networks and present practical recommendations based on our findings. We anticipate that this study will help scientists and engineers to design unrolled networks for their applications and diagnose problems within their networks efficiently.

Joint Optimization of Multiple Resources for Distributed Service Deployment in Satellite Edge Computing Networks Abstract PDF

Jiachen Sun, Xu Chen, Zhen Li, Jiawei Wang, Yuxi Chen

IEEE Internet of Things Journal, 2024

With the emergence of mobile edge applications and the demand for access-as-a-service, satellite mobile edge computing stands out as a disruptive technology for delivering low-latency edge service. In this article, we focus on service deployment to the edge satellites for terrestrial users, which is a key enabling technology in satellite mobile edge computing and will replace traditional centralized cloud computing. Most existing works on service deployment consider a centralized nonconvex optimization problem with high computational overhead. However, in practice, it is difficult for a single satellite to solve computationally expensive network optimization problems. To this end, we propose a distributed optimization model based on the alternating direction method of multipliers (ADMMs), which can relieve the computational burden by leveraging collaborative calculations among multiple satellites. Our proposed model minimizes the total delay of service deployment for terrestrial users by formulating a joint optimization problem that involves deployment decisions, CPU resource decisions, transmission decisions, and caching decisions. Furthermore, we propose a novel approximation method that transforms the nonconvex optimization problem to a convex one to make the joint optimization problem solvable in polynomial time. Finally, we conduct experiments using scaled global population data and show that the proposed distributed model outperforms the baselines.

Causal Inference
Generative Modeling
Scientific Discovery
Statistical Learning

Top-k Feature Importance Ranking Abstract PDF

Yuxi Chen, Tiffany Tang, Genevera Allen

Transactions on Machine Learning Research (TMLR), 2025

Accurate ranking of important features is a fundamental challenge in interpretable machine learning with critical applications in scientific discovery and decision-making. Unlike feature selection and feature importance, the specific problem of ranking important features has received considerably less attention. We introduce RAMPART (Ranked Attributions with MiniPatches And Recursive Trimming), a framework that utilizes any existing feature importance measure in a novel algorithm specifically tailored for ranking the top-k features. Our approach combines an adaptive sequential halving strategy that progressively focuses computational resources on promising features with an efficient ensembling technique using both observation and feature subsampling. Unlike existing methods that convert importance scores to ranks as post-processing, our framework explicitly optimizes for ranking accuracy. We provide theoretical guarantees showing that RAMPART achieves the correct top-k ranking with high probability under mild conditions, and demonstrate through extensive simulation studies that RAMPART consistently outperforms popular feature importance methods, concluding with two high-dimensional genomics case studies.

2025

Top-k Feature Importance Ranking Abstract PDF

Yuxi Chen, Tiffany Tang, Genevera Allen

Transactions on Machine Learning Research (TMLR), 2025

Accurate ranking of important features is a fundamental challenge in interpretable machine learning with critical applications in scientific discovery and decision-making. Unlike feature selection and feature importance, the specific problem of ranking important features has received considerably less attention. We introduce RAMPART (Ranked Attributions with MiniPatches And Recursive Trimming), a framework that utilizes any existing feature importance measure in a novel algorithm specifically tailored for ranking the top-k features. Our approach combines an adaptive sequential halving strategy that progressively focuses computational resources on promising features with an efficient ensembling technique using both observation and feature subsampling. Unlike existing methods that convert importance scores to ranks as post-processing, our framework explicitly optimizes for ranking accuracy. We provide theoretical guarantees showing that RAMPART achieves the correct top-k ranking with high probability under mild conditions, and demonstrate through extensive simulation studies that RAMPART consistently outperforms popular feature importance methods, concluding with two high-dimensional genomics case studies.

Deep Memory Unrolled Networks for Solving Imaging Linear Inverse Problems Abstract PDF Slides

Yuxi Chen, Xi Chen, Shirin Jalali, Arian Maleki

Sampling Theory and Applications (SampTA), 2025 (Oral)

Unrolled networks have emerged as one of the most successful methods in imaging applications. Although they have demonstrated remarkable efficacy in solving specific computer vision and computational imaging tasks, their adaptation to other applications presents considerable challenges. This is primarily due to the multitude of design decisions that practitioners working on new applications must navigate, each potentially affecting the network's overall performance. These decisions include selecting the optimization algorithm to unroll, defining the loss function, deciding on the structure of residual connections, and determining the number of convolutional layers, among others. Compounding the issue, evaluating each design choice requires time-consuming simulations to train the neural network. As a result, the process of exploring multiple options and identifying the optimal configuration becomes time-consuming and computationally demanding. The main objectives of this paper are (1) to unify some ideas and methodologies used in unrolled networks to reduce the number of design choices a user has to make, and (2) to report a comprehensive numerical study to discover the optimal design choices. We anticipate that this study will help scientists and engineers design unrolled networks for their applications and diagnose problems within their networks efficiently.

Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problems Abstract PDF

Yuxi Chen, Xi Chen, Arian Maleki, Shirin Jalali

Entropy (Special Issue on Advances in Computational Imaging), 2025

Unrolled networks have become prevalent in various computer vision and imaging tasks. Although they have demonstrated remarkable efficacy in solving specific computer vision and computational imaging tasks, their adaptation to other applications presents considerable challenges. This is primarily due to the multitude of design decisions that practitioners working on new applications must navigate, each potentially affecting the network's overall performance. These decisions include selecting the optimization algorithm, defining the loss function, and determining the deep architecture, among others. Compounding the issue, evaluating each design choice requires time-consuming simulations to train, fine-tune the neural network, and optimize its performance. As a result, the process of exploring multiple options and identifying the optimal configuration becomes time-consuming and computationally demanding. The main objectives of this paper are (1) to unify some ideas and methodologies used in unrolled networks to reduce the number of design choices a user has to make, and (2) to report a comprehensive ablation study to discuss the impact of each of the choices involved in designing unrolled networks and present practical recommendations based on our findings. We anticipate that this study will help scientists and engineers to design unrolled networks for their applications and diagnose problems within their networks efficiently.

2024

Joint Optimization of Multiple Resources for Distributed Service Deployment in Satellite Edge Computing Networks Abstract PDF

Jiachen Sun, Xu Chen, Zhen Li, Jiawei Wang, Yuxi Chen

IEEE Internet of Things Journal, 2024

With the emergence of mobile edge applications and the demand for access-as-a-service, satellite mobile edge computing stands out as a disruptive technology for delivering low-latency edge service. In this article, we focus on service deployment to the edge satellites for terrestrial users, which is a key enabling technology in satellite mobile edge computing and will replace traditional centralized cloud computing. Most existing works on service deployment consider a centralized nonconvex optimization problem with high computational overhead. However, in practice, it is difficult for a single satellite to solve computationally expensive network optimization problems. To this end, we propose a distributed optimization model based on the alternating direction method of multipliers (ADMMs), which can relieve the computational burden by leveraging collaborative calculations among multiple satellites. Our proposed model minimizes the total delay of service deployment for terrestrial users by formulating a joint optimization problem that involves deployment decisions, CPU resource decisions, transmission decisions, and caching decisions. Furthermore, we propose a novel approximation method that transforms the nonconvex optimization problem to a convex one to make the joint optimization problem solvable in polynomial time. Finally, we conduct experiments using scaled global population data and show that the proposed distributed model outperforms the baselines.

Teaching

Carnegie Mellon University Teaching Assistant

46-932 Simulation Methods in Option Pricing

Spring 2026

This course initially presents standard topics in simulation including random variable generation, statistical analysis of simulation output and variance reduction methods including antithetic variables, control variables, importance sampling, conditional Monte Carlo, stratification and martingale control variables.

46-929 Financial Time Series Analysis

This course is an introduction to financial time series analysis. We will cover basic time series models (AR, MA, ARMA and ARIMA) and their use in financial applications, including forecasting and the development of quantitative trading strategies.

36-401 Modern Regression

Fall 2025

This course is an introduction to applied data analysis using linear regression modeling. We will derive properties about those models, apply and examine various models for real datasets, assess the validity of modeling assumptions, and determine what conclusions we can make (if any) from those models.

Eric Chen

Bio

News

Publications

Teaching