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 theoretical foundations of machine learning as a basis for human intelligence; in particular, I focus on robustness, representation learning, and out-of-distribution generalization. I work to develop principled formal analyses of the statistical and algorithmic properties of these tasks and possible approaches to solving them.

[Google Scholar] [CV]

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

Conference Publications:

The Risks of Invariant Risk Minimization
ICLR 2021 (To Appear)
(Also Appeared) NeurIPS 2020 Workshop: Causal Discovery & Causality-Inspired Machine Learning

Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski
[arXiv] [CMU AI Seminar] [2 minute spotlight presentation]

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] [Zico's Simons Talk]

Workshops and Manuscripts:

An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization
Under Review
(Short Version) ICLR 2021 Workshop: RobustML

Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski
[arXiv]

Self-Reflective Variational Autoencoder
ICLR 2021 Workshop: Hardware Aware Efficient Training

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]