About Me
Hello!
I am a Postdoctoral Researcher at NYU Center for Data Science, working with Shirley Ho (Flatiron Institute, NYU), Julia Kempe (NYU), and Uroš Seljak (UC Berkeley). I completed my PhD at Inria (MIND Team), Université Paris-Saclay under the supervision of Alexandre Gramfort (Meta) and Pedro L. C. Rodrigues (Inria, Grenoble).
My research focuses on probabilistic machine learning, simulation-based inference and generative modeling, with applications in neuroscience, cosmology, and beyond. I am most excited about how AI can transform the way we do science.
News
Sept 2025: Started postdoc at NYU Center for Data Science.
August 2025: New tutorial paper on Simulation-Based Inference out with Max Planck collaborators. link to paper
Dec 2024: Successfully defended my PhD at Inria Saclay. link to video
Research
The primary focus of my research has been on the use of deep generative models (normalizing flows and diffusion models) in simulation-based inference (SBI). The goal is to develop methods for more accuracte, efficient and reliabile inference on complex biophysical simulators - in neuroscience, astrophysics and beyond. Ultimately, my research seeks to build greater trust in AI as a tool for scientific discovery.
Current Directions
Scaling simulation-based inference for cosmology, while deepening my expertise in generative models and theoretical machine learning. This work is in close collaboration with colleagues at NYU CDS, the Flatiron Institute / Polymathic AI, and UC Berkeley. Stay tuned…
Main PhD projects
- Development of new validation diagnostics for conditional deep generative models [1, 2], with an integration to the official
sbipython package from the MACKELAB. - Exploration of novel posterior sampling algorithms using deep generative models, for example based on diffusion models when one wishes to condition on multiple observations to get more precise parameter estimations [3]. This is collaborative work with Sylvain Le Corff (LPSM - Sorbonne Université) and Gabriel V. Cardoso (CMAP - École Polytechnique).
- Application of SBI to neuroscience time series (EEG) data [4].
Other
Before my PhD, I had the chance to work more closely on ML applications in Medical Imaging at two different start-ups, Covera Health in New York (uncertainty quantification of Deep Learning models on MRIs) and Owkin in Paris (development of Deep Learning models for breast cancer survival analysis on histology images and their calibration).
Open Source
I am an active contributor to the sbi Python toolbox.
CV
Here is my CV. For more details, feel free to contact me at julia.linhart@nyu.edu :)
References
[1] Julia Linhart, Alexandre Gramfort and Pedro L. C. Rodrigues, Validation Diagnostics for SBI algorithms based on Normalizing Flows, ML4PS Workshop, NeurIPS 2022.
[2] Julia Linhart, Alexandre Gramfort and Pedro L. C. Rodrigues, L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference, NeurIPS 2023.
[3] Julia Linhart, Gabriel V. Cardoso, Alexandre Gramfort, Sylvain Le Corff and Pedro L. C. Rodrigues, Diffusion posterior sampling for simulation-based inference in tall data settings, 2024.
[4] Julia Linhart, Pedro L. C. Rodrigues, Thomas Moreau, Gilles Louppe, Alexandre Gramfort, Neural Posterior Estimation of hierarchical models in neuroscience, Colloque GRETSI 2022.