Philipp Nazari

MsC in Mathematics at ETH

I am an upcoming CLS PhD student in Computer science advised by Konstantin Rusch (affiliated with the ELLIS institute and the Max Planck Institute for Intelligent Systems) and Fanny Yang from ETH. Previously, I obtained my Bachelors in Physics and Mathematics from Heidelberg university where I was affiliated with the lab of Fred Hamprecht, as well as a master in mathematics from ETH Zurich, where I wrote my thesis in the lab of Helmut Bölcskei.

I am boradly interested in geoetric deep learning, its applications to the natural sciences and fundamentals of ML.

news

Mar 02, 2025	I am excited to start my PhD with Konstantin Rusch and Fanny Yang starting in summer of 2025

selected publications

Geometric Autoencoders-What You See is What You Decode

Philipp Nazari, Sebastian Damrich, and Fred A Hamprecht

In International Conference on Machine Learning, 2023

Abs PDF

Visualization is a crucial step in exploratory data analysis. One possible approach is to train an autoencoder with low-dimensional latent space. Large network depth and width can help unfolding the data. However, such expressive networks can achieve low reconstruction error even when the latent representation is distorted. To avoid such misleading visualizations, we propose first a differential geometric perspective on the decoder, leading to insightful diagnostics for an embedding’s distortion, and second a new regularizer mitigating such distortion. Our “Geometric Autoencoder” avoids stretching the embedding spuriously, so that the visualization captures the data structure more faithfully. It also flags areas where little distortion could not be achieved, thus guarding against misinterpretation.