Jianyi Yang
I am an Assistant Professor in the Department of Computer Science at the University of Houston. I received my PhD degree from University of California, Riverside in 2023, advised by Prof. Shaolei Ren. I was a visiting research assistant at Caltech and UC Riverside during 2023-2024, working with Prof. Adam Wierman and Prof. Shaolei Ren.
My research interests span AI/ML algorithms and their applications in computing systems. My research seeks to advance trustworthy and efficient AI, building resilient, responsible, and efficient AI systems. Recent research methodologies include reinforcement learning, online learning/optimization, learning-augmented algorithms, knowledge informed learning etc.
Our research team at UH focuses on trustworthy AI, generative models, and learning for computing systems. If you are interested in joining our team, please send me an email with your CV and official transcripts. Please start you email title with “Application for AI@UH”.
news
| Dec 9, 2025 |  Our paper 3D-Learning: Diffusion-Augmented Distributionally Robust Decision-Focused Learning is accepted by IEEE INFOCOM 2026. This paper exploits diffusion models to construct the adversarail environments for Predict-Then-Optimize (PTO) problems and trains distributionally robust prediction models. Congratulations to Jiaqi. |
|---|---|
| Sep 25, 2025 | Our paper Distributionally Robust Optimization via Diffusion Ambiguity Modeling was accepted by OPT 2025 collocated with NeurIPS 2025! This paper builds a diffusion-based ambiguity set for Distributionally Robust Optimization (DRO) problems. |
| Sep 20, 2025 | I was invited to give a talk at Hewlett Packard Enterprise Data Science Institute (HPE-DSI) on October. |
| Jul 15, 2025 | I will server in the Technical Program Committee of e-Energy’26 |
| Jul 1, 2025 | I will server in the Technical Program Committee of SIGMETRICS’26 |
| Jan 19, 2025 | Our paper Learning-Augmented Online Control for Decarbonizing Water Infrastructures has been accepted by e-Energy’25! This paper provides a learning-augmented control algorithm for a critical infrastructure: the municipal water supply systems. The algorithm guarantees the worst-case safety of water supply (e.g. for fire protection) while minizing the energy costs for pumping water. |
| Sep 25, 2024 | Our paper Online Budgeted Matching with General Bids has been accepted by NeurIPSs 2024! It provides a provable algorithm to solve online budgeted matching problem with general bids. Manuscript will come out soon. |
| Sep 25, 2024 | Our paper Learning-Augmented Decentralized Online Convex Optimization in Networks has been accepted by ACM SIGMETRICS’25! It proposes a novel algorithm to provably robustify machine learning predictions for decentralized optimization in networks. |
| May 1, 2024 | Our paper Building Socially-Equitable Public Models was accepted by ICML 2024! |
| Dec 13, 2023 | Our paper Online Allocation with Replenishable Budgets: Worst Case and Beyond was accepted by ACM SIGMETRICS 2024! This paper provides fundamental algorithms with worst-case guarantees for online resource allocation problem and proposes a learning-augmented algorithm to improve the statistical performance under worst-case guarantee. |