- All Categories
- Featured Events
- Alumni
- Application Deadline
- Arts
- Campus Discourse
- Careers
- BU Central
- Center for the Humanities
- Charity & Volunteering
- Kilachand Center
- Commencement
- Conferences & Workshops
- Diversity & Inclusion
- Examinations
- Food & Beverage
- Global
- Health & Wellbeing
- Keyword Initiative
- Lectures
- LAW Community
- Meetings
- Orientation
- Other Events
- Religious Services & Activities
- Special Interest to Women
- Sports & Recreation
- Social Events
- Study Abroad
- Weeks of Welcome
- DOM Medical Education Retreat8:00 am
- Sustainability Innovation Seed Grant Program Launch9:00 am
- SE PhD Final Defense of Ruidi Chen10:00 am
- MSE Masters Thesis Presentation of Ze Niu10:00 am
- IS&T RCS Tutorial - Introduction to Python, Part One10:00 am
- IS&T RCS Tutorial - Introduction to C++ Programming, Part One12:15 pm
- IS&T RCS Tutorial - Introduction to R1:00 pm
- IS&T RCS Tutorial - Introduction to Python, Part One2:30 pm
- Global Job Search for International Students4:00 pm
- Global Job Search for International Students4:00 pm
- Career Directions: Getting Started with the CCD5:00 pm
- Ecumenical Night Prayer5:30 pm
- Book Club5:30 pm
- Monday Night Football at Fuller's BU Pub6:00 pm
- Community Service Center Open House 6:00 pm
- Community Dinner6:00 pm
- Employer On Campus: Bates White Economic Consulting6:00 pm
SE PhD Final Defense of Ruidi Chen
TITLE: DISTRIBUTIONALLY ROBUST LEARNING UNDER THE WASSERSTEIN METRIC
ABSTRACT: We develop a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data usingDistributionally Robust Optimization (DRO) under the Wasserstein metric. The learning problems that are studied in thisdissertation include: (i) Distributionally Robust Linear Regression (DRLR), which estimates a robustified linear regressionplane by minimizing the worst-case expected absolute loss over a probabilistic ambiguity set characterized by theWasserstein metric; (ii) Groupwise Wasserstein Grouped LASSO (GWGL), which aims at inducing sparsity at a group level when there exists a predefined grouping structure for the predictors, through defining a specially structured Wasserstein metric for DRO; (iii) Optimal decision making using DRLR informed K-Nearest Neighbors (KNN) estimation, which selects among a set of actions the optimal one through predicting the outcome under each action using KNN with a distance metric weighted by the DRLR solution; and (iv) Distributionally Robust Multivariate Learning, which solves a DRO problem with a multi-dimensional response/label vector, as in Multivariate Linear Regression (MLR) and Multiclass Logistic Regression (MLG), which generalize the univariate response model addressed in DRLR. We derive a tractable DRO relaxation for each problem, establishing a connection between robustness and regularization, obtain upper bounds on the predictionand estimation errors of the solution, and verify the accuracy and robustness of the estimator through a series of syntheticand real data experiments. The experiments with real data are all associated with various health informatics applications, an application area which motivated the work in this thesis. In addition to estimation (regression and classification) we also consider outlier detection applications.
COMMITTEE: ADVISORYannis Paschalidis, SE/ECE; David Castanon, SE/ECE; Dimitris Bertsimas, ORC, MIT; Venkatesh Saligrama, SE/ECE;CHAIR, Alexander Olshevsky, SE/ECE
When | 10:00 am to 12:00 pm on Monday, September 9, 2019 |
---|---|
Location | 8 Saint Mary's Street, Room 404 |