Andres Potapczynski

  • PhD in Data Science, NYU
  • MSc in Data Science, Columbia
  • BSc in Applied Mathematics, ITAM
  • BA in Economics, ITAM

Research & Projects

Low-Precision Arithmetic for Fast Gaussian Processes
We study the different failure modes that can occur when training GPs in half precision. To circumvent these failure modes, we propose a multi-faceted approach involving conjugate gradients with re-orthogonalization, mixed precision, and preconditioning -- 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022).

Bias-Free Scalable Gaussian Processes via Randomized Truncations
Studies the biases introduced by approximate methods and eliminates them via randomized truncation estimators -- 38th International Conference on Machine Learning (ICML 2021).

Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
Introduces a family of continuous relaxations that is more flexible, extensible and better performing than the Gumbel-Softmax -- 34th Conference on Neural Information Processing Systems (NeurIPS 2020).

Nowcasting with Google Trends
Proposes an alternative kernel bandwidth selection algorithm and exhibits what Google searches are relevant for predicting unemployment, influenza outbreaks and violence spikes in Mexico. The content is in English (past the acknowledgments) and relevant pages are: 4, 26, 36, 43, 48 -- Undergraduate Thesis.

Classifying webpages based on their menu
By modifying Word2Vec we recover an embedding that helps to cluster clients based on their webpage's menu content -- Capstone Project.