Sanae Lotfi


PhD student at New York University

I am a PhD student at the Center for Data Science at NYU and a DeepMind fellow, advised by Professor Andrew Gordon Wilson. I am currently interested in understanding and quantifying the generalization of deep learning models. More broadly, my research interests include out-of-distribution generalization in deep learning, statistical learning theory and inference, Bayesian learning, probabilistic modeling, large-scale optimization, and loss surface analysis.

Prior to NYU, I obtained a master’s degree in applied mathematics from Polytechnique Montreal. I was fortunate to work there with Professors Andrea Lodi and Dominique Orban to design stochastic first- and second-order algorithms with compelling theoretical and empirical properties for machine learning and large-scale optimization. I also hold an engineering degree in general engineering and applied mathematics from CentraleSupélec.

You can contact me at

Google Scholar, LinkedIn, Twitter, Github


Dangers of Bayesian Model Averaging under Covariate Shift
Pavel Izmailov, Patrick Nicholson, Sanae Lotfi, Andrew Gordon Wilson
Neural Information Processing Systems (NeurIPS), 2021
[arxiv, code]

Evaluating Approximate Inference in Bayesian Deep Learning
Andrew Gordon Wilson, Pavel Izmailov, Matthew D Hoffman, Yarin Gal, Yingzhen Li, Melanie F Pradier, Sharad Vikram, Andrew Foong, Sanae Lotfi, Sebastian Farquhar
NeurIPS 2021 Competition

Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
Gregory W. Benton, Wesley J. Maddox, Sanae Lotfi, Andrew Gordon Wilson
International Conference on Machine Learning (ICML), 2021
[arxiv, code]

Stochastic Damped L-BFGS with Controlled Norm of the Hessian Approximation
Sanae Lotfi, Tiphaine B. de Ruisselet, Dominique Orban, Andrea Lodi
NeurIPS Optimization for Machine Learning Workshop, 2020
Spotlight presentation

Stochastic First and Second Order Optimization Methods for Machine Learning
Sanae Lotfi
Master’s Thesis, 2020
Polytechnique Montreal