Kevin Jamieson

About

Kevin Jamieson is an Associate Professor in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. He holds the title of Paul G. Allen Career Development Professor in Computer Science & Engineering and is also an Adjunct faculty member in the Department of Statistics. Jamieson received his B.S. in 2009 from the University of Washington, his M.S. in 2010 from Columbia University, and his Ph.D. in 2015 from the University of Wisconsin – Madison, all in electrical engineering. After completing a postdoctoral fellowship in the AMP lab at the University of California, Berkeley, working with Benjamin Recht, he returned to the University of Washington as faculty in 2017. His research focuses on leveraging already-collected data to inform future measurements in a closed-loop system, a process known as active learning. This approach allows for extracting richer insights than fixed measurement plans within the same statistical budget. Jamieson’s work spans from theoretical foundations to practical algorithms with guarantees, and includes open-source machine learning systems. His research has been applied in various domains such as measuring human perception in psychology studies, adaptive A/B/n testing in dynamic web environments, numerical optimization, and hyperparameter selection for deep neural networks. His contributions to the field have been recognized through awards including an NSF CAREER award and an Amazon Faculty Research award.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Algorithm
• Mathematical optimization
• Mathematics
• Combinatorics
• Discrete mathematics
• Information Retrieval
• World Wide Web

Selected publications

• A System for Massively Parallel Hyperparameter Tuning

  Proceedings of Machine Learning and Systems · 2020 · 161 citations

• An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits

  arXiv (Cornell University) · 2020 · 20 citations

  Senior authorCorresponding

  This paper proposes near-optimal algorithms for the pure-exploration linear bandit problem in the fixed confidence and fixed budget settings. Leveraging ideas from the theory of suprema of empirical processes, we provide an algorithm whose sample complexity scales with the geometry of the instance and avoids an explicit union bound over the number of arms. Unlike previous approaches which sample based on minimizing a worst-case variance (e.g. G-optimal design), we define an experimental design o…

  DOI

• Identifying New Podcasts with High General Appeal Using a Pure Exploration Infinitely-Armed Bandit Strategy

  2022 · 7 citations

  Podcasting is an increasingly popular medium for entertainment and discourse around the world, with tens of thousands of new podcasts released on a monthly basis. We consider the problem of identifying from these newly-released podcasts those with the largest potential audiences so they can be considered for personalized recommendation to users. We first study and then discard a supervised approach due to the inadequacy of either content or consumption features for this task, and instead propose…

  PublisherDOI

• High-Dimensional Experimental Design and Kernel Bandits

  arXiv (Cornell University) · 2021 · 6 citations

  Senior authorCorresponding

  In recent years methods from optimal linear experimental design have been leveraged to obtain state of the art results for linear bandits. A design returned from an objective such as $G$-optimal design is actually a probability distribution over a pool of potential measurement vectors. Consequently, one nuisance of the approach is the task of converting this continuous probability distribution into a discrete assignment of $N$ measurements. While sophisticated rounding techniques have been propo…

• CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning

  2024-01-01 · 2 citations

  article
  PublisherDOI

Recent grants

• CIF: Small: Online Learning and Optimal Experiment Design with a Budget

  NSF · $500k · 2020–2024

Frequent coauthors

• Lalit Jain

  33 shared

• Robert D. Nowak

  22 shared

• Andrew Wagenmaker

  22 shared

• Max Simchowitz

  19 shared

• Maya R. Gupta

  17 shared

• Simon S. Du

  16 shared

• Hyrum S. Anderson

  Robust Chip (United States)

  16 shared

• Julian Katz-Samuels

  15 shared

Labs

• Kevin Jamieson's LabPI

  Not provided

Education

• B.S., Electrical Engineering

  University of Washington

  2009

• M.S., Electrical Engineering

  Columbia University

  2010

• Ph.D., Electrical Engineering

  University of Wisconsin - Madison

  2015

Awards & honors

• NSF CAREER award
• Amazon Faculty Research award

Similar researchers at University of Washington

• Dieter Foxh-107
• Ali Farhadih-91
• Jeffrey Heerh-80