Jingwei Ji

Ph.D. student in Management Science and Engineering at Stanford University.

Email: jingwei [dot] ji [at] stanford [dot] edu
Advisor: Renyuan Xu

Google Scholar | GitHub

Research

Decision making under structured data environments (e.g., weak-to-strong, multi-task learning); online learning and bandits; stochastic optimization; sequential search and selection problems; risk-aware decision making; off-policy evaluation (including post-training for RLVR).

Published Papers

• Risk-Aware Linear Bandits: Theory and Applications in Smart Order Routing. Jingwei Ji, Renyuan Xu, Ruihao Zhu. Operations Research, 2026.
• The Pandora's Box Problem with Sequential Inspections. Ali Aouad, Jingwei Ji, Yaron Shaposhnik. Operations Research, 2026.
• Foresee the Next Line: On Information Disclosure in Tandem Queues. Ran Snitkovsky, Ricky Roet-Green, Jingwei Ji. Operations Research, 2025.

Working Papers

• Weak-to-Strong Learning in Decision Making. Jingwei Ji, Renyuan Xu.
• Multi-Task Dynamic Pricing in Credit Market with Contextual Information. Adel Javanmard, Jingwei Ji, Renyuan Xu.
• Online Optimization of Difference-of-Convex Compositions with Smooth Mappings. Jingwei Ji, Jong-Shi Pang, Renyuan Xu.
• Risk of Bad Tails: CVaR-Aware Pandora's Box and Prophet Inequalities. Jingwei Ji.