Comet Calendar Event Details

Mathematical Sciences Distinguished Colloquium by Meimei Liu
Tuesday, Jan. 14
1:30 p.m. - 2:30 p.m. Location: SLC 2.302

Meimei Liu
Duke University
Reproducible Bootstrap Aggregating

Heterogeneity between training and testing data degrades reproducibility of a well-trained model. In modern applications, how to deploy a trained model in a different domain is becoming an urgent question raised by many domain scientists. In this paper, we propose a reproducible bootstrap aggregating (Rbagging) method coupled with a new algorithm, the iterative nearest neighbor sampler (INNs), effectively drawing bootstrap samples from training data to mimic the distribution of the testing data. Rbagging is a general ensemble framework that can be applied to  most classifiers. We further propose Rbagging+ to effectively detect outliers in the testing data.

Our theoretical results show that the resamples based on Rbagging have the same distribution as the testing data. Moreover, under suitable assumptions, we further provide a general bound to control the test excess risk of the ensemble classifiers. The proposed method is compared with several other popular domain adaptation methods via extensive simulation studies and real applications including medical diagnosis and imaging classifications.

Coffee to be served 30 minutes prior to the talk in the alcove outside of FO 2.406.

 

Persons with disabilities may submit a request for accommodations to participate in this event at UT Dallas' ADA website. You may also call (972) 883-5331 for assistance or send an email to [email protected]. All requests should be received no later than 2 business days prior to the event.
Contact Info:
Viswanath Ramakrishna, 972-883-6873
Questions? Email me.

Tagged as Lectures/Seminars, Professional Dev.
See more events from Natural Sciences & Mathematics
View other events on the Comet Calendar