Michael P. Kim



I am a Miller Postdoctoral Fellow at UC Berkeley, working with Shafi Goldwasser. Prior to this, I completed my Ph.D. in the Stanford Theory Group under the sage guidance of Omer Reingold.

My research investigates foundational questions about responsible machine learning. Much of this work aims to (1) identify ways in which machine-learned predictors can exhibit unfair discrimination and (2) develop algorithmic tools that provably mitigate such forms of discrimination. More broadly, I am interested in how the computational lens (i.e. algorithms and complexity theory) can help tackle emerging societal and scientific challenges.

phd thesis

A Complexity-Theoretic Perspective on Fairness
Stanford University 2020

publications & manuscripts

Universal Adaptability: Target-Independent Inference that Competes with Propensity Scoring
MPK, Christoph Kern, Shafi Goldwasser, Frauke Kreuter, Omer Reingold
PNAS 2022

Beyond Bernoulli: Generating Random Outcomes that cannot be Distinguished from Nature
Cynthia Dwork, MPK, Omer Reingold, Guy N. Rothblum, Gal Yona
to appear ALT 2022

Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration [arXiv]
Shengjia Zhao, MPK, Roshni Sahoo, Tengyu Ma, Stefano Ermon
NeurIPS 2021

mcboost: Multi-Calibration Boosting for R
Florian Pfisterer, Christoph Kern, Susanne Dandl, Matthew Sun, MPK, Bernd Bischl
The Journal of Open Source Software 2021

Outcome Indistinguishability [arXiv] [ECCC]
Cynthia Dwork, MPK, Omer Reingold, Guy N. Rothblum, Gal Yona
STOC 2021

A Distributional Framework for Data Valuation [arXiv]
Amirata Ghorbani, MPK, James Zou
ICML 2020

Preference-Informed Fairness [arXiv]
MPK, Aleksandra Korolova, Guy N. Rothblum, Gal Yona
ITCS 2020

Evidence-Based Rankings
Cynthia Dwork, MPK, Omer Reingold, Guy N. Rothblum, Gal Yona
FOCS 2019

Tracking and Improving Information in the Service of Fairness [arXiv]
Sumegha Garg, MPK, Omer Reingold
EC 2019

Multiaccuracy: Black-Box Post-Processing for Fairness in Classification [arXiv]
MPK, Amirata Ghorbani, James Zou
AAAI AI, Ethics, and Society 2019

On Estimating Edit Distance: Alignment, Dimension Reduction, and Embeddings [arXiv]
Moses Charikar, Ofir Geri, MPK, William Kuszmaul
ICALP 2018

Fairness Through Computationally-Bounded Awareness [arXiv]
MPK, Omer Reingold, Guy N. Rothblum
NeurIPS 2018

Calibration for the (Computationally-Identifiable) Masses [arXiv]
Úrsula Hébert-Johnson, MPK, Omer Reingold, Guy N. Rothblum
ICML 2018

Who Can Win a Single-Elimination Tournament? [arXiv]
MPK, Warut Suksompong, Virginia Vassilevska Williams
AAAI 2016, SIAM J. Discrete Math. 2017

Fixing Tournaments for Kings, Chokers, and More
MPK and Virginia Vassilevska Williams
IJCAI 2015

Synthesis of Enantiopure, Trisubstituted Cryptophane-A Derivatives
O. Taratula, MPK, Y. Bai, J.P. Philbin, B.A. Riggle, D.N. Haase, and I.J. Dmochowski. Organic Letters 2012
In a previous life, I studied Chemistry.