Elan Rosenfeld

Hi! I'm a PhD student in the Machine Learning Department at CMU where I am fortunate to be advised by Pradeep Ravikumar and Andrej Risteski. Before entering grad school I was a software engineer at Google NYC where I worked on Search Infrastructure. Before that I graduated from CMU with degrees in computer science and statistics & machine learning.

I'm broadly interested in the foundational aspects of human intelligence that we take for granted, in particular robustness, representation learning, and out-of-distribution generalization. I'm also intrigued by the seemingly sub-optimal choices we make as described by cumulative prospect theory and the potential benefits of such behavior.

[Google Scholar] [CV]

You can reach me at [firstname] at cmu.edu

Conference Publications:

Certified Robustness to Label-Flipping Attacks via Randomized Smoothing
ICML 2020

Elan Rosenfeld, Ezra Winston, Pradeep Ravikumar, Zico Kolter
[arXiv] [virtual poster/presentation] [slides] [blog post]

Certified Adversarial Robustness via Randomized Smoothing
ICML 2019

Jeremy Cohen, Elan Rosenfeld, Zico Kolter
[arXiv] [code] [short ICML talk]

Manuscripts and Preprints:

The Risks of Invariant Risk Minimization
Under Review

Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski
[arXiv]

Self-Reflective Variational Autoencoder
Under Review

Ifigeneia Apostolopoulou, Elan Rosenfeld, Artur Dubrawski
[arXiv]

Human-Usable Password Schemas: Beyond Information-Theoretic Security
CMU Senior Thesis
Awarded “Exemplary Senior Honors Thesis”

Elan Rosenfeld, Santosh Vempala, Manuel Blum
[arXiv] [poster]