Sung Min (Sam) Park


Email: spark AT csail mit edu

Office: 32G-822

GitHub | Twitter | CV



Hi! I am a PhD student at MIT EECS, advised by Prof. Aleksander Mądry.

I work on machine learning, focusing on problems related to robustness.



I received a BS in Computer Science from Cornell University in 2014, where I was fortunate to work with Prof. Ramin Zabih and Prof. Bobby Kleinberg.

Previously at MIT, I worked on understanding statistical-computational tradeoffs in high-dimensional statistics with Prof. Guy Bresler for my SM thesis.

In the past, I have interned at Waymo, Dropbox, and Google.



Datamodels: Predicting Predictions from Training Data
Andrew Ilyas*, Sung Min Park*, Logan Engstrom*, Guillaume Leclerc, Aleksander Mądry
ICML 2022
[arxiv] [blog part 1 part 2] [data]

On Distinctive Properties of Universal Perturbations
Sung Min Park, Kuo-An Wei, Kai Xiao, Jerry Li, Aleksander Mądry

Sparse PCA from Sparse Linear Regression
(α-β order) Guy Bresler, Sung Min Park, Madalina Persu
NeurIPS 2018
[arxiv] [poster] [code]

On the Equivalence of Sparse Statistical Problems
Sung Min Park
SM thesis 2016

Structured learning of sum-of-submodular higher order energy functions
Alexander Fix, Thorsten Joachims, Sung Min Park, Ramin Zabih
ICCV 2013


Other writings

Fourier Theoretic Probabilistic Inference over Permutations
Cornell, Spring 2014

Analysis of pipage method for k-max coverage
Cornell, Fall 2012



Fast Forward Computer Vision (FFCV)



I grew up in Seoul and Singapore, where I attended SAS.

From 2016-18, I served in the Republic of Korea Army.

In my free time, I like lifting, rowing, playing basketball, and learning physics.