Stephen Mussmann

Steve is an IFDS postdoc at the University of Washington Computer Science working with Kevin Jamieson and Ludwig Schmidt.  He received his PhD in 2021 from Stanford University Computer Science advised by Percy Liang. His research studies data aspects of machine learning, such as Active Learning, Data Filtering/Pruning, and Experimental Design.

I will be joining Georgia Tech School of Computer Science as an assistant professor in Fall 2024! I am looking for PhD students: please feel free to reach out if you are interested in working with me! For the 2023-2024 academic year, I will be working at Coactive.


Office: CSE2 232


Google Scholar


LabelBench: A Comprehensive Framework for Benchmarking Label-Efficient Learning

Jifan Zhang, Yifang Chen, Gregory Canal, Stephen Mussmann, Yinglun Zhu, Simon Shaolei Du, Kevin Jamieson, Robert D Nowak

June, 2023

      Data Subset Selection via Machine Teaching

Stephen Mussmann, Alex Fang, Ludwig Schmidt, Kevin Jamieson

October, 2022


      Constants Matter: The Performance Gains of Active Learning

Stephen Mussmann, Sanjoy Dasgupta

International Conference on Machine Learning (ICML), 2022

      Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation

Mayee Chen, Benjamin Cohen-Wang, Stephen Mussmann, Frederic Sala, Christopher Re

International Conference on Artificial Intelligence and Statistics (AISTATS), 2021

On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks

Stephen Mussmann*, Robin Jia*, Percy Liang

Findings of Empirical Methods in Natural Language Processing (EMNLP), 2020

Concept Bottleneck Models

Pang Wei Koh*, Thao Nguyen*, Yew Siang Tang*, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang

International Conference on Machine Learning (ICML), 2020

Selection via Proxy: Efficient Data Selection for Deep Learning

Cody Coleman, Christopher Yeh, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang,  Jure Leskovec, Matei Zaharia

International Conference on Learning Representations (ICLR), 2020

A Tight Analysis of Greedy Yields Subexponential Time Approximation for Uniform Decision Tree

Ray Li, Percy Liang, Stephen Mussmann

Symposium on Discrete Algorithms (SODA), 2020 

Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss

Stephen Mussmann, Percy Liang

Neural Information Processing Systems (NeurIPS), 2018

On the Relationship between Data Efficiency and Error for Uncertainty Sampling

Stephen Mussmann, Percy Liang

International Conference on Machine Learning (ICML), 2018

The Price of Debiasing Automatic Metrics in Natural Language Evaluation

Arun Chaganty*, Stephen Mussmann*, Percy Liang

Association for COmputational Linguistics (ACL), 2018

Generalized Binary Search For Split-Neighborly Problems

Stephen Mussmann, Percy Liang

International Conference on Artificial Intelligence and Statistics (AISTATS), 2018

Fast Amortized Inference and Learning in Log-linear Models with Randomly Perturbed Nearest Neighbor Search

Stephen Mussmann*, Daniel Levy*, Stefano Ermon

Uncertainty in Artificial Intelligence (UAI), 2017

Learning and Inference via Maximum Product Search

Stephen Mussmann, Stefano Ermon

International Conference on Machine Learning (ICML), 2016

Incorporating Assortativity and Degree Dependence into Scalable Network Models

Stephen Mussmann*, John Moore*, Joseph J. Pfeiffer III, Jennifer Neville

AAAI Conference on Artificial Intelligence (AAAI), 2015