Bojian Hou

AI Research Scientist, Meta

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

1 paper

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization

#716 · Parvin Nazari, Bojian Hou, Davoud Ataee Tarzanagh, Li Shen, George Michailidis

We propose a novel search direction for stochastic online bilevel optimization, enabling first- and zeroth-order algorithms to achieve sublinear regret without window smoothing.