About me
I am a PhD student in Econometrics and Statistics at the University of Chicago Booth School of Business, where I am fortunate to be advised by Professor Veronika Ročková and co-advised by Professor Bahar Taşkesen. My research interests are in statistical machine learning, with a particular focus on generative modeling and network experiments.
Before coming to Chicago, I earned my bachelor’s degree in Economics and Data Science from Bocconi University in 2024, where I was advised by Professor Omiros Papaspiliopoulos.
Publications, Preprints, and Working Papers
Publication
-
Bengusu Nar, Jiguang Li, Veronika Ročková, and Panos Toulis. “Dynamic Treatment on Networks.” NeurIPS 2026. Paper
NetworksReinforcement learning
Working papers
-
Bengusu Nar, Bahar Taşkesen, Ya-Ping Hsieh, and Veronika Ročková. “Preventing Memorization in Diffusion Models via Fisher-Rao Guidance.” Working paper.
Diffusion modelsInformation geometry -
Bengusu Nar, Ya-Ping Hsieh, Bahar Taşkesen, Teng Andrea Xu, Veronika Ročková, and Bryan Kelly. “Synthetic Markets, Real Forecasts: Fisher–Rao Diffusion for Asset Returns.” Working paper.
Generative modelingAsset pricing
Updates
Dynamic Treatment on Networks was accepted to NeurIPS 2026.
Preventing Memorization in Diffusion Models via Fisher-Rao Guidance was accepted to the DynaFront workshop at NeurIPS 2026.
Presented Dynamic Treatment on Networks at the ISBA World Meeting in Nagoya.