Pan Xu

Journal article Crit Care Explor · February 1, 2026 CONTEXT: Management of ventilator and venovenous extracorporeal membrane oxygenation (ECMO) settings in critically ill adults requires individualized decisions to balance oxygenation, ventilation, and complication risks. Existing approaches rely heavily on ... Full text Link to item Cite

Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning

Journal article Transactions on Machine Learning Research · January 1, 2026 We study offline off-dynamics reinforcement learning (RL) to utilize data from an easily accessible source domain to enhance policy learning in a target domain with limited data. Our approach centers on return-conditioned supervised learning (RCSL), partic ... Open Access Cite

Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer

Journal article Transactions on Machine Learning Research · January 1, 2025 Decision Transformer (DT) has emerged as a promising class of algorithms in offline reinforcement learning (RL) tasks, leveraging pre-collected datasets and Transformer’s capabil-ity to model long sequences. Recent works have demonstrated that using parts ... Open Access Cite

Efficient and robust sequential decision making algorithms

Journal article AI Magazine · September 1, 2024 Sequential decision-making involves making informed decisions based on continuous interactions with a complex environment. This process is ubiquitous in various applications, including recommendation systems and clinical treatment design. My research has c ... Full text Cite

Challenges of COVID-19 Case Forecasting in the US, 2020-2021.

Journal article PLoS Comput Biol · May 2024 During the COVID-19 pandemic, forecasting COVID-19 trends to support planning and response was a priority for scientists and decision makers alike. In the United States, COVID-19 forecasting was coordinated by a large group of universities, companies, and ... Full text Open Access Link to item Cite

Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits

Journal article Transactions on Machine Learning Research · January 1, 2024 Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. Often, the environment in which the data are collected differs from the environ ... Open Access Cite

Pre-trained Hypergraph Convolutional Neural Networks with Self-supervised Learning

Journal article Transactions on Machine Learning Research · January 1, 2024 Hypergraphs are powerful tools for modeling complex interactions across various domains, including biomedicine. However, learning meaningful node representations from hypergraphs remains a challenge. Existing supervised methods often lack generalizability, ... Open Access Cite

Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning

Journal article Performance Evaluation Review · June 19, 2023 We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of their entropy-regularized long-term rewards. To overcome the curse of dimensiona ... Full text Open Access Cite

Multiple models for outbreak decision support in the face of uncertainty.

Journal article Proc Natl Acad Sci U S A · May 2, 2023 Policymakers must make management decisions despite incomplete knowledge and conflicting model projections. Little guidance exists for the rapid, representative, and unbiased collection of policy-relevant scientific input from independent modeling teams. I ... Full text Open Access Link to item Cite

Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning

Journal article Proceedings of the ACM on Measurement and Analysis of Computing Systems · February 28, 2023 We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of their entropy-regularized long-term rewards. To overcome the curse of dimensiona ... Full text Open Access Cite

The United States COVID-19 Forecast Hub dataset.

Journal article Sci Data · August 1, 2022 Academic researchers, government agencies, industry groups, and individuals have produced forecasts at an unprecedented scale during the COVID-19 pandemic. To leverage these forecasts, the United States Centers for Disease Control and Prevention (CDC) part ... Full text Open Access Link to item Cite

Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States.

Journal article Proc Natl Acad Sci U S A · April 12, 2022 Short-term probabilistic forecasts of the trajectory of the COVID-19 pandemic in the United States have served as a visible and important communication channel between the scientific modeling community and both the general public and decision-makers. Forec ... Full text Open Access Link to item Cite

Stochastic nested variance reduction for nonconvex optimization

Journal article Journal of Machine Learning Research · May 1, 2020 We study nonconvex optimization problems, where the objective function is either an average of n nonconvex functions or the expectation of some stochastic function. We propose a new stochastic gradient descent algorithm based on nested variance reduction, ... Open Access Cite

Stochastic variance-reduced cubic regularization methods

Journal article Journal of Machine Learning Research · August 1, 2019 We propose a stochastic variance-reduced cubic regularized Newton method (SVRC) for non-convex optimization. At the core of SVRC is a novel semi-stochastic gradient along with a semi-stochastic Hessian, which are specifically designed for cubic regularizat ... Open Access Cite