Biostatistics Seminars

The Department of Biostatistics at the University of Michigan is proud to invite leading scholars from around the world to visit Ann Arbor to share their expertise, wisdom and experience. All are welcome to attend these seminars, which are held in-person.

Join the Seminar Email List

Hilary Finucane, PhD

Associated Scientist in the Program in Medical and Population Genetics; Associate Member in the Genetics Program at the Stanley Center for Psychiatric Research
Broad Institute

Learn more about this presenter

DATE: Thursday, January 18, 2024
TIME: 3:30 p.m.
LOCATION: SPH I, Room 1690

TITLE: To be announced

ABSTRACT: To be announced

TOPICS: To be announced

Marc Suchard, MD, PhD

Professor of Biostatistics, Biomathematics, & Human Genetics
University of California, Los Angeles

Learn more about this presenter

DATE: Thursday, January 25, 2024
TIME: 3:30 p.m.
LOCATION: SPH I, Room 1690

TITLE: To be announced

ABSTRACT: To be announced

TOPICS: To be announced

Edward Kennedy, PhD

Associate Professor, Statistics and Data Science
Carnegie Mellon University

Learn more about this presenter

DATE: Thursday, February 08, 2024
TIME: 3:30 p.m.
LOCATION: SPH I, Room 1690

TITLE: To be announced

ABSTRACT: To be announced

TOPICS: Causal Inference, Health Policy, High-Dimensional Data, Machine Learning, Nonparametric / Semiparametric Modeling, Personalized Medicine, Precision Health

Yong Chen, PhD

Professor, Biostatistics
University of Pennsylvania

Learn more about this presenter

DATE: Thursday, February 22, 2024
TIME: 3:30 p.m.
LOCATION: SPH I, Room 1690

TITLE: To be announced

ABSTRACT: To be announced

TOPICS: To be announced

Debdeep Pati, PhD

Professor, Statistics
Texas A&M University

Learn more about this presenter

DATE: Thursday, March 14, 2024
TIME: 3:30 p.m.
LOCATION: SPH I, Room 1690

TITLE: Bayesian fair clustering

ABSTRACT: The advent of ML-driven decision-making and policy formation has led to an increasing focus on algorithmic fairness. As clustering is one of the most commonly used unsupervised machine learning approaches, there has naturally been a proliferation of literature on fair clustering. A popular notion of fairness in clustering mandates the clusters to be balanced, i.e., each level of a protected attribute must be approximately equally represented in each cluster. Building upon the original framework developed in Chierichetti et al. (NeurIPS, 2017), this literature has rapidly expanded in various aspects. In this article, we offer a novel model-based formulation of fair clustering, complementing the existing literature which is almost exclusively based on optimizing appropriate objective functions. We first rigorously define a notion of fair clustering in the population level under a model mis-specified framework, with minimal assumptions on the data-generating mechanism. We then specify a Bayesian model equipped with a novel hierarchical prior specification to encode the notion of balance in resulting clusters, and whose posterior targets this population-level object. A carefully developed collapsed Gibbs sampler ensures efficient computation, with a key ingredient being a novel scheme for non-uniform sampling from the space of binary matrices with fixed margins, utilizing techniques from optimal transport towards constructing proposals. Impressive empirical success of the proposed methodology is demonstrated across varied numerical experiments, and benchmark data sets. Importantly, the benefits of our approach are not merely limited to the specific model we propose -- thinking from a generative modeling perspective allows us to provide concrete guidelines for prior calibration that ensures desired distribution of balance a-priori, develop a concrete notion of optimal recovery in the fair clustering problem, and device schemes for principled performance evaluations of algorithms.

TOPICS: Bayesian Statistics, Nonparametric / Semiparametric Modeling