About

Hi! I am a final-year PhD student at MIT EECS and CSAIL, fortunate to be advised by Prof. Aleksander Mądry.

[News] I’m on the job market! Primarily looking for postdoc positions beginning ~Fall 2024 and relevant positions in industry research.

I’m broadly interested in understanding and improving machine learning (ML) methodology. In particular, I’m interested in viewing ML models through the lens of data:

• How do we attribute model predictions back to training data?
• How do we find latent structure (e.g., subpopulations) in our datasets automatically in a way that’s faithful to the model (rather than human priors)?
• Can we derive insights about ML phenomena (e.g., scaling laws, emergence) through this lens?

 

Bio

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

Earlier during my PhD, I was supported by the MIT Akamai Presidential Fellowship and the Samsung Scholarship.

Prior to grad school, 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.

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

 

Research

The Journey, Not the Destination: How Data Guides Diffusion Models
Kristian Georgiev*, Josh Vendrow*, Hadi Salman, Sung Min Park, Aleksander Mądry
In preparation, 2023.

TRAK: Attributing Model Behavior at Scale
Sung Min Park*, Kristian Georgiev*, Andrew Ilyas*, Guillaume Leclerc, Aleksander Mądry
ICML 2023 (Oral presentation)
[arxiv] [blog][code] [website]

ModelDiff: A Framework for Comparing Learning Algorithms
Harshay Shah*, Sung Min Park*, Andrew Ilyas*, Aleksander Mądry
ICML 2023
[arxiv] [blog][code]

FFCV: Accelerating Training by Removing Data Bottlenecks
Guillaume Leclerc, Andrew Ilyas, Logan Engstrom, Sung Min Park, Hadi Salman, Aleksander Mądry
CVPR 2023
[code]

A Data-Based Perspective on Transfer Learning
Saachi Jain*, Hadi Salman*, Alaa Khaddaj*, Eric Wong, Sung Min Park, Aleksander Mądry
CVPR 2023
[arxiv] [blog]

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] [code][data]

On Distinctive Properties of Universal Perturbations
Sung Min Park, Kuo-An Wei, Kai Xiao, Jerry Li, Aleksander Mądry
2021
[arxiv]

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
[pdf]

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

 

Talks

• May 2023 LIDS & Stats Tea
• May 2023 MIT MLTea
• Apr 2023 ML Collective Reading group
• Feb 2023 MIT LIDS Student Conference
• Aug 2022 UMN ML Seminar
• Feb 2022 LIDS & Stats Tea
• Jan 2022 MIT LIDS Student Conference

 

Misc

Region Detection and Geometry Prediction
Patent from work during Summer 2020 internship at Waymo
[pdf]

Fourier Theoretic Probabilistic Inference over Permutations
Cornell, Spring 2014
[pdf]

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

 

Personal

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

From 2016-18, I served in the Republic of Korea Army, where I met an amazing group of people and spent most of my free time trying to learn QFT.

In my free time, I enjoy lifting, playing basketball, rowing, watching the NBA, and learning physics.