Skip to main content

Scheduled Colloquia

Spring 2026

All talks will take place in New Cabell Hall 389 at 12:30 pm unless stated otherwise.

Expand content
Expand content

February 19: Jinbo Chen, UPenn

Assessing Algorithm Fairness Requires Adjustment for Risk Distribution Differences: Re-considering the Equal Opportunity Criterion

Abstract: The increasing use of predictive algorithms to assist clinical decision making has generated strong calls for systematic fairness assessment. Equal opportunity, a popular fairness criterion, demands parity in true positive rates (TPRs) across population subgroups. We identify a fundamental but under-recognized weakness in this criterion: even when a model perfectly captures underlying risk within each subgroup, TPRs will generally differ at any given threshold whenever the true risk distributions vary across subgroups. Neglecting these distributional differences risks erroneous claims of performance inequity. To correct for this, we propose the adjusted true positive rate (aTPR), which normalizes subgroup TPRs against the risk distribution of a reference subgroup. The corresponding adjusted fairness metric, the aTPR difference, better operationalizes equal treatment for equal risk by evaluating whether individuals with comparable true risks would receive comparable opportunities for high-risk classification, independent of subgroup membership. We validate the metric through simulation studies and demonstrate its application on an electronic health record cohort to evaluate a six-month mortality prediction model designed to enhance palliative care referral timing.

Expand content

February 26: Jordan Bryan, UVA

Rescheduled from 2/12/2026. 

Efficient use of endmember variability for spectral unmixing

Abstract: The spectrum of a mixed substance can be described as a weighted linear combination of pure source, or "endmember," spectra. In many physical science applications, endmember spectra exhibit variability, which can be observed by looking at examples assembled in a spectral library. Given such a library, we examine the problem of estimating the endmember abundance weights corresponding to an observed mixed spectrum. We contribute two statistical perspectives to this unmixing problem, which suggest best practices for leveraging endmember variability and highlight circumstances under which efficient estimators of abundance weights may achieve significant variance reduction relative to default methods. Using real-world spectral datasets representing several physical science domains, we show that spectral data tend to possess the characteristics necessary to realize these gains.

Expand content

March 12: Yuqi Gu, Columbia

Information coming soon.

Expand content

March 19: Qixuan Chen, Columbia

Information coming soon.

Expand content

April 2: Emma Zhang, Emory

Information coming soon.

Expand content

April 9: Shiying Li, UNL

Information coming soon.

Expand content

April 16: Ziqiao Wang, UVA

Information coming soon.

Expand content

April 23: Charles Doss, UMinnesota

Information coming soon.


Fall 2025

All talks will take place in Wilson 214 at 12:30 pm. You can also access to the talks through this link.

Expand content
Expand content

September 11: Paul Torrey, University of Virginia

Information coming soon.

Expand content

September 25: Ji-Hyun Lee, University of Florida

Information coming soon.

Expand content

October 2: Ahnaf Rafi, University of Virginia

Information coming soon.

Expand content

October 9: Qingning Zhou, UNC Charlotte

Information coming soon.

Expand content

October 23: Weichen Wang, University of Hong Kong

Information coming soon.

Expand content

November 6: Ted Enamorado, Washington University

Information coming soon.

Expand content

November 13: Fadoua Balabdaoui, ETH Zurich (remote only)

Information coming soon.

Expand content

December 4: Xiaocong Xu, University of Southern California

Information coming soon.


Spring 2025

All talks will take place in Clark G004 at 12:30 pm. You can also access to the talks through this link.

Expand content
Expand content

February 13: Nicholas Landry, University of Virginia (UVA)

Information coming soon.

Expand content

February 20: No Colloquium

No Colloquium scheduled

Expand content

February 27: Oh-Ran Kwon, University of Southern California (USC)

Information coming soon.

Expand content

March 6: Michele Guindani, University of California, Los Angeles (UCLA)

Information coming soon.

Expand content

March 13: Spring Recess – No Colloquium

Information coming soon.

Expand content

March 27: Yanxun Xu, Johns Hopkins University (JHU)

Information coming soon.

Expand content

April 3: Ran Tao, Vanderbilt University

Information coming soon.

Expand content

April 10: Dehan Kong, University of Toronto

Information coming soon.

Expand content

April 17: Fangzheng Xie, Indiana University

Information coming soon.

Expand content

April 24: Ted Enamorado, Washington University in St. Louis

Information coming soon.