Othmane Mazhar

Postdoctoral Researcher Institut Louis Bachelier
Hosted within Fondation du Risque
Chair in Artificial Intelligence and Quantitative Methods for Finance
Paris, France

Previously, I was a postdoctoral researcher at the Laboratoire de Probabilités, Statistique et Modélisation, Sorbonne University and Université Paris Cité, from 2023 to 2026.

Research interests

I develop mathematical and statistical foundations for learning, generating, and controlling stochastic systems from dependent data. My work connects finite-sample statistics, optimal transport, stochastic control, and computational PDE methods.

My current programme focuses on Schrödinger–Bass transport, learning stochastic-bridge dynamics, path-space probability, and quantitative stability guarantees for generated path laws.

News

September 2026. Our paper with Huyên Pham, Direct Estimation of Schrödinger Bridge Time-Series Drifts: Finite-Sample, Asymptotic, and Adaptive Guarantees , was accepted to the NeurIPS 2026 Main Track.
September 2026. New preprint: A Constructive Solution to Talagrand’s Gaussian Convexification Problem .
2026. I joined the Institut Louis Bachelier as a postdoctoral researcher, hosted within Fondation du Risque.
2026. I was recognized as a Gold Technical Reviewer for the International Conference on Machine Learning.
April 2026. New preprint with Alexandre Alouadi, Grégoire Loeper, Célian Marsala, and Huyên Pham: SBBTS: A Unified Schrödinger–Bass Framework for Synthetic Financial Time Series .
March 2026. New preprint with Pierre Henry-Labordère, Grégoire Loeper, Huyên Pham, and Nizar Touzi: Bridging Schrödinger and Bass: A Semimartingale Optimal Transport Problem with Diffusion Control .

Recent publications

O. Mazhar. A Constructive Solution to Talagrand’s Gaussian Convexification Problem. Preprint, 2026. arXiv
O. Mazhar and H. Pham. Direct Estimation of Schrödinger Bridge Time-Series Drifts: Finite-Sample, Asymptotic, and Adaptive Guarantees. Accepted to NeurIPS 2026 Main Track. arXiv · code
A. Alouadi, G. Loeper, C. Marsala, O. Mazhar, and H. Pham. SBBTS: A Unified Schrödinger–Bass Framework for Synthetic Financial Time Series. Under review, 2026. arXiv · code
P. Henry-Labordère, G. Loeper, O. Mazhar, H. Pham, and N. Touzi. Bridging Schrödinger and Bass: A Semimartingale Optimal Transport Problem with Diffusion Control. Under review, 2026. arXiv
A. Alouadi, P. Henry-Labordère, G. Loeper, O. Mazhar, H. Pham, and N. Touzi. LightSBB-M: Bridging Schrödinger and Bass for Generative Diffusion Modeling. Under review, 2026. arXiv · code