I am a scientist working with Prof. Daniel Kuhn at the College of Management of Technology from EPFL and Prof. Andreas Krause at the Computer Science Department from ETH Zurich. Prior to that, I got my PhD in Operations Research from University of Illinois at Urbana-Champaign, advised by Prof. Xin Chen and Prof. Niao He.
My research interest lies in data-driven decision-making with problems arising from optimization, operations research, and data science. Specifically, I am interested in designing simple and efficient algorithms with provable guarantees for stochastic optimization, bandit and reinforcement learning. I am also interested in operations management like supply chain and revenue management. Recently, I start to interpret statistics problems as optimization and design efficient computational methods.
I am always open to discussions! See Research for my research directions, Publication for my papers and Presentation for slides and posters.
yifan.hu@epfl.ch Google Scholar
INFORMS Annual Meeting 2024
I will present "Contextual Stochastic Bilevel Optimization and Three-Stage Stochastic Programming" on Sunday Oct 20, 2:15pm - 2:35pm in Summit 424.
My collaborator will present "Landscape of Policy Gradient Objectives for Finite Horizon MDPs: Applications in Operations Models" on Sunday Oct 20, 11:03am - 11:21am in Summit 337.
News
Oct 2024. Grant. Our proposal on "Sustainable Supply Chain via Data-Driven Innovation" got accepted. It will support a PhD student for four years at EPFL.
Oct 2024. Presentations.
I gave two guest lectures at the statistics department in Rutgers University, New Brunswick.
I am invited to give an oral presentation at the Cornell ORIE Young Researcher Workshop!
I will give seminars at the statistics department and the MSIS department in Rutgers University, New Brunswick.
I will give a talk at INFORMS Annual Meeting in Seattle.
Sep. 2024. New Paper. Our new paper "Landscape of Policy Optimization for Finite Horizon MDPs with General State and Action" is available online. It established the benign nonconvex landscape of finite horizon MDP in control, inventory, and cash-balance problems.
Sep. 2024. Paper Acceptance. Three papers got accepted to NeurIPS 2024. See you in Vancouver!
Sep 5th, 2024. Talk. I gave a talk at OR2024 "Stochastic Hidden Convex Optimization in Network Revenue Management."
Aug 20th, 2024. Paper. Our paper "Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles" is available online. This is the extended version of my earlier work in NeurIPS 2021.
Aug 5th, 2024. Paper. Our paper "Efficient Algorithms for A Class of Stochastic Hidden Convex Optimization and Its Applications in Network Revenue Management" got accepted by Operations Research.
Jul. 2024. Talks. I gave two talks at International Symposium on Mathematical Programming in Montreal, Canada.
Stochastic Optimization under Hidden Convexity.
Three-stage Stochastic Programming is As Easy As Classical Stochastic Optimization.
Jun. 2024. Paper. Our paper "Stochastic Bilevel Optimization with Lower-Level Contextual Markov Decision Processes" is online. First time being the last author!
May. 2024. Papers. Two preprints are available online.
Apr. 2024. Funding. Our proposal got approved by NCCR Automation of Swiss NSF, Switzerland. It supports a PhD for four years.
Mar. 2024. Talk. I organized a session and gave a talk at INFORMS Optimization Society Conference in Houston.
Session: Decision Making with Side Information.
Feb. 2024. Grant. Our proposal got accepted. The grant will support a PhD student for four years at ETH Zurich or EPFL.
Feb. 2024. Paper. Our paper got a minor revision at Operations Research!
Jan. 2024. Papers. Two papers got accepted to AISTATS 2024!